SlideShare a Scribd company logo
1 of 121
Building Artificial
General Intelligence
Peter Morgan
www.deeplp.com
https://start.activestate.com/oreilly-ebook/
© Peter Morgan, May 2019
Outline of Talk
• Physical Systems
• Biological
• Non-biological
• Deep Learning
• Description
• Types
• Reinforcement Learning
• Latest Research
• Towards AGI
• Overview
• Comparisons
• Building AGI
• Conclusions
© Peter Morgan, May 2019
Motivation
• Solve (general) intelligence
• Use it to solve everything else
• Medicine
• Cancer
• Brain disease (Alzheimer's, etc.)
• Longevity
• Physics
• Maths
• Materials science
• Social
© Peter Morgan, May 2019
What is Intelligence?
© Peter Morgan, May 2019
© Peter Morgan, May 2019
How will we get
there?
Physics
Computer
Science
Neuroscience
© Peter Morgan, May 2019
It takes a village to create an AGI
Psychology
Physical Systems
• Biological
• Plants, bacteria, insects, reptiles, mammalian, biological brains
• Classical (non-biological)
• CPU - Intel Xeon SP, AMD RyZen, Qualcomm, IBM PowerPC, ARM
• GPU - Nvidia (Volta), AMD (Vega)
• FPGA - Intel (Altera, Xylinx etc.)
• ASIC - Google TPU, Graphcore IPU, Intel Nervana, Wave, …
• Neuromorphic (Human Brain Project - SpiNNaker, BrainScaleS; IBM TrueNorth; Intel Liohi, …
• Quantum
• IBM, Microsoft, Intel, Google, DWave, Rigetti, …
• Quantum biology? (photosynthesis, navigation, …)
• QuantumML, Quantum Intelligence
© Peter Morgan, May 2019
Types of Physical Computation Systems*
*Can we find a theory that unifies them all (classical, quantum, biological, non-biological)
Digital Neuromorphic
Quantum Biological
© Peter Morgan, May 2019
Biology
© Peter Morgan, May 2019
Biological
Systems are
Hierarchical
© Peter Morgan, May 2019
Biological
Neuron
Microstructure
© Peter Morgan, May 2019
Biological
Neuron
© Peter Morgan, May 2019
Hand drawn neuron
types
From "Structure of the Mammalian Retina"
c.1900, by Santiago Ramon y Cajal.
© Peter Morgan, May 2019
Neuron -
scanning
electron
microscope
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Cortical
columns in
the cortex
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Human
Connectome
© Peter Morgan, May 2019
Central
Nervous
System (CNS)
© Peter Morgan, May 2019
Social
Systems
© Peter Morgan, May 2019
A
Comparison
of Neuron
Models
© Peter Morgan, May 2019
Non-biological
Hardware
• Digital
• CPU
• GPU
• FPGA
• ASIC
• Neuromorphic
• Various architectures
• SpiNNaker, BrainScaleS, TrueNorth, …
• Quantum
• Different qubits
• Anyons, superconducting, photonic, …
© Peter Morgan, May 2019
Digital
Computing
• Abacus
• Charles Babbage
• Ada Lovelace
• Vacuum tubes (valves)
• Turing
• Von Neumann
• ENIAC
• Transistor (Bardeen, Brattain, Shockey, 1947)
• Intel
• ARM
• Nvidia
• ASICs
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Cray-1
1976
160 MFlops
© Peter Morgan, May 2019
CPU – Intel
Xeon
Up to 32 cores, ~1 TFlops
© Peter Morgan, May 2019
GPU –
Nvidia Volta
V100
21 billion transistors, 120 TFlops
© Peter Morgan, May 2019
DGX-2 - released Mar 2018
16 V100’s, 2 PFlops, 30TB storage ($400k) 2 PFlops!
© Peter Morgan, May 2019
ASIC – Google TPU 3.0
© Peter Morgan, May 2019 360 TFlops! - Announced Google I/O, May 2018
ASIC - Graphcore IPU
© Peter Morgan, May 2019 >200 TFlops
© Peter Morgan, May 2019
Cloud TPU’s
© Peter Morgan, May 2019
Over 100 PetaFlops !
Summit US
IBM AC922 system
4,608 servers
Each server contains two
22-core IBM Power9 CPUs
six Nvidia Tesla V100 GPUs
 200PFlops (3 ExaFlops
mixed precision!)
2 tennis courts area
250 Petabytes storage
13MW power
$200million
Announced 5 June 2018
© Peter Morgan, May 2019
HPC –
what’s
next?
Currently 200PFlops - Summit
By 2020 – beyond Exascale
© Peter Morgan, May 2019
HPC
Timeline
© Peter Morgan, May 2019
Aurora 21
© Peter Morgan, May 2019
Exascale compute by 2021, Argonne National Lab, Intel + Cray © Peter Morgan, June 14 2018
Processor
Performance
(MFlops)
More specific 
© Peter Morgan, May 2019
Biology vs
Digital
© Peter Morgan, May 2019
Neuromorphic
Computing
• Biologically inspired
• First proposed Carver Mead, Caltech, 1980’s
• Uses analogue signals – spiking neural networks (SNN)
• SpiNNaker (Manchester, HBP, Furber)
• BrainScaleS (Heidelberg, HBP, Schemmel)
• TrueNorth (IBM, Modha)
• Intel Liohi
• Startups (Knowm, Spaun, etc.)
• Up to 1 million cores, 1 billion “neurons” (mouse)
• Need to scale 100X  human brain
• Relatively low power
• Available on the (HBP) cloud today
© Peter Morgan, May 2019
SpiNNaker
Neuromorphic
Computer
© Peter Morgan, May 2019
Neuromorphic
vs von
Neumann
© Peter Morgan, May 2019
TrueNorth
Performance
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Neuromorphic v ASIC
Analogue v Digital
© Peter Morgan, May 2019
Quantum
Computing
• First proposed by Richard Feynman, Caltech, 1980’s
• Qubits – spin 1, 0 and superposition states (QM)
• (Nature is) fundamentally probabilistic at atomic scale
• Have to be kept cold (mKelvin) to avoid
noise/decoherence
• Building is an engineering problem (theory is known)
• Several approaches - superconductors, trapped ions,
semiconductors, topological structures
• Several initiatives (with access available)
• Microsoft, IBM, Google, Intel, Dwave, Rigetti, etc.
• Can login today
• Many applications – optimization, cryptography, drug
discovery, etc.
© Peter Morgan, May 2019
IBM 50 Qubit
Quantum
Computer
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Quantum Logic Gates
© Peter Morgan, May 2019
Summary – Now have three non-biological stacks
Algorithms
Distributed Layer
OS
Hardware
Classical Neuromorphic Quantum
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Outline
• Physical Systems
• Biological
• Non-biological
• Deep Learning
• Description
• Types
• Reinforcement Learning
• Latest Research in DL
• Towards AGI?
• Overview
• Comparisons
• AGI
• Conclusions
© Peter Morgan, May 2019
Early papers
© Peter Morgan, May 2019
Nodes and Layers
© Peter Morgan, May 2019
© Peter Morgan, May 2019
More Neural Networks (“Neural Network Zoo”)
© Peter Morgan, May 2019
Computation in each node
© Peter Morgan, May 2019
Universal Approximation Theorem
• A feed-forward network with a single hidden layer containing a finite number
of neurons, can approximate continuous functions in Rn, under mild assumptions on the
activation function
• We can define as an approximate realization of f(x):
• One of the first versions of the theorem was proved by George Cybenko in 1989
for sigmoid activation functions
• Kurt Hornik showed in 1991 that it is not the specific choice of the activation function, but
rather the multilayer feedforward architecture which gives neural networks the potential
of being universal approximators
• Cybenko, G., Approximations by superpositions of sigmoidal functions, Mathematics of
Control, Signals, and Systems, 2(4), 303-314, 1989
• Kurt Hornik (1991) Approximation Capabilities of Multilayer Feedforward Networks,
Neural Networks, 4(2), 251–257, 1991
© Peter Morgan, May 2019
Computation Graph
https://www.tensorflow.org/programmers_guide/graph_viz
© Peter Morgan, May 2019
Hyperparameters
• Activation function
• Optimizations
• Loss (cost) function
• Learning rate
• Initialization
• Batch normalization
• Automation
• Hyperparameter tuning
• AutoML
• https://research.googleblog.com/2018/03/using-machine-learning-to-discover.html
© Peter Morgan, May 2019
Deep
Learning
Performance
Image classification
© Peter Morgan, May 2019
Deep Learning Performance
ImageNet Error rate is now around 2.2%, less than half that of average humans
© Peter Morgan, May 2019
Convolutional Neural
Networks
• First developed in 1970’s.
• Widely used for image recognition and
classification.
• Inspired by biological processes, CNN’s
are a type of feed-forward ANN.
• The individual neurons are tiled in such a
way that they respond to overlapping
regions in the visual field
• Yann LeCun – Bell Labs, 90’s
© Peter Morgan, May 2019
Recurrent Neural Networks
• First developed in 1970’s.
• RNN’s are neural networks that
are used to predict the next
element in a sequence or time
series.
• This could be, for example,
words in a sentence or letters in
a word.
• Applications include predicting
or generating music, stories,
news, code, financial instrument
pricing, text, speech, in fact the
next element in any event
stream.
© Peter Morgan, May 2019
GANs
Generative Adversarial Networks - introduced
by Ian Goodfellow et al in 2014 (see references)
A class of artificial intelligence algorithms used
in unsupervised deep learning
A theory of adversarial examples, resembling
what we have for normal supervised learning
Implemented by a system of two neural
networks, a discriminator, D and a generator, G
D & G contest with each other in a zero-sum
game framework
Generator generates candidate networks and
the discriminator evaluates them
© Peter Morgan, May 2019
Stacked Generative Adversarial Networks
https://arxiv.org/abs/1612.04357v1
© Peter Morgan, May 2019
NN Models
AlexNet (Toronto)
VGG (Oxford)
ResNet (Microsoft)
Inception (Google)
DenseNet (Cornell)
SqueezNet (Berkeley)
MobileNet (Google)
NASNet (Google)
And many (hundreds) more ...
© Peter Morgan, May 2019
Deep
Learning
Frameworks
© Peter Morgan, May 2019
Top 20 ML/DL Frameworks
KD Nuggets Feb 2018 https://www.kdnuggets.com/2018/02/top-20-python-ai-machine-learning-open-source-projects.html
* Deep Learning
o Machine Learning
*
MXNet
*CNTK
© Peter Morgan, May 2019
TensorFlow
• TensorFlow is the open sourced deep learning library from Google (Nov 2015)
• It is their second generation system for the implementation and deployment of
large-scale machine learning models
• Written in C++ with a python interface, originated from research and deploying
machine learning projects throughout a wide range of Google products and
services
• Initially TF ran only on a single node (your laptop, say), but now runs on distributed
clusters
• Available across all the major cloud providers (TFaaS)
• Second most popular framework on GitHub
• Over 100,000 stars as of May 2018
• https://www.tensorflow.org/
© Peter Morgan, May 2019
TensorFlow supports many platforms
RaspberryPi
Android
iOS
TPU
GPU
CPU
CloudTPU © Peter Morgan, May 2019
Growth of Deep Learning atGoogle
and many more . . ..
Directories containing model descriptionfiles
© Peter Morgan, May 2019
TensorFlow Popularity
© Peter Morgan, May 2019
Other
Frameworks
• CNTK (Microsoft)
• MXnet (Amazon)
• Keras (Open source community)
• PyTorch (Facebook)
• Neon (Intel)
• Chainer (Preferred Networks)
© Peter Morgan, May 2019
Data Sets
• Text, speech, images, video, time series
• Examples - MNIST and Labeled Faces in the Wild (LFW).
MNIST LFW
© Peter Morgan, May 2019
Open Source
• ML Frameworks – open source (e.g., TensorFlow)
• Operating systems – open source (Linux)
• Hardware – open source (OCP = Open Compute Project)
• Data sets – open source (see previous slide)
• Research – open source (see arXiv)
• The fourth industrial revolution will be (is) open source
© Peter Morgan, May 2019
Reinforcement
Learning
• Goal driven
• Reward and penalty
• TD Learning
• DQN
• AlphaGo
• Latest research
• http://metalearning-symposium.ml
© Peter Morgan, May 2019
RL Research
Directions
• Deep Reinforcement Learning Symposium, NIPS 2017
• https://sites.google.com/view/deeprl-symposium-
nips2017/home
• Berkeley (BAIR) http://bair.berkeley.edu
• Peter Abdeel
• Serge Levine
• Deepmind https://deepmind.com
• IMPALA (DMLab)
https://deepmind.com/blog/impala-scalable-
distributed-deeprl-dmlab-30/
• OpenAI https://openai.com
• Research white papers
• Graphcore - Bristol ASIC company
• https://www.graphcore.ai/posts/directions-of-ai-
research
© Peter Morgan, May 2019
Outline
• Physical Systems
• Biological
• Non-biological
• Deep Learning
• Description
• Types
• Reinforcement Learning
• Latest Research in DL
• Towards AGI
• Overview
• Comparisons
• Building AGI
• Conclusions
© Peter Morgan, May 2019
Towards AGI
• What do we need?
• Active Inference
• Other approaches
• Applications
• Building AGI
AGI = Artificial General Intelligence
© Peter Morgan, May 2019
© Peter Morgan, May 2019
© Peter Morgan, May 2019
© Peter Morgan, May 2019
© Peter Morgan, May 2019
Comparisons - ANN vs BNN
• Neural circuits in the brain develop via synaptic pruning; a process by which connections
are overproduced and then eliminated over time
• In contrast, computer scientists typically design networks by starting with an initially
sparse topology and gradually adding connections
• AI (specific) vs AGI (general)
• Yann LeCun – CNN’s Bell Labs in ’80/90’s – “mathematical, not biological”
• Gone as far as we can with ”just” mathematics
• Now almost every researcher looking to biology for inspiration
• Costa et al, 2018, etc. (see “Bio-plausible Deep Learning” in reference section)
ANN = Artificial Neural Networks
BNN = Biological Neural Networks
© Peter Morgan, May 2019
Approaches to AGI
• Helmholtz (Late 1800’s)
• Friston – Active Inference
• Tishby – Information bottleneck
• Bialek – Biophysics
• Hutter - AIXI
• Schmidhuber – Godel Machine
• Etc.
© Peter Morgan, May 2019
Active Inference
• Free Energy Principle
• Systems act to minimize their expected free energy
• Reduce uncertainty (or surprisal)
• F = Complexity – Accuracy
• Prediction error = expected outcome – actual outcome = surprise
• Theory of Everything (ToE)
• In physics - try to unify gravity and quantum mechanics  call this a ToE
• But actually Active Inference is more encompassing than even this
• It encompasses all interactions and dynamics (physical phenomena)
• Over all time scales
• Over all distance scales
• Also see Constructor Theory
• David Deutsch (Oxford)
© Peter Morgan, May 2019
What are the principles?
Newtonian
mechanics – three
laws
Special relativity –
invariance of laws
under a Lorentz
transformation
GR – Principle of
Equivalence
Electromagnetism
– Maxwell’s
equations
Thermodynamics –
three laws
Quantum
mechanics –
uncertainty
principle
Relativistic QM –
Dirac equation
Dark energy/dark
matter – we don’t
know yet
All of the above =
Principle of Least
Action
© Peter Morgan, May 2019
Key Concepts
Bayesian
inference
Predictive
coding
Generative
models
Cortical
organization
Perception Action
Learning
Decision
making
Affect
(emotional
intelligence)
Computational
psychiatry
Developmental
psychology
Social
interactions
General Hierarchical Cognitive
Analogy – Einstein’s General Theory of Relativity
• Made some very general (and insightful)
assumptions about the laws of physics in a
gravitational field (non-inertial frames)
• Equivalence principle
• Covariance of laws of physics
• Generalised coordinate system –
Riemannian geometry
• Spacetime is curved
• Standing on the shoulders of giants
• After ten years of hard work he finally
wrote down his now famous field equations
© Peter Morgan, May 2019
All known physics – Field theoretic
© Peter Morgan, May 2019
Active Inference - Information theoretic (uses generalised free energy)
( ) argmin E [ ( , )] [ ( ) || ( )]
( ) argmin ( , )
( , ) E [ln ( | ) ln ( , | )]
ln ( ) ( , )
( , ) E [ln ( | ) ln ( , | )]
Q
Q
entropy energy
Q
entropy energy
Q F D Q P
Q s F
F Q s P o s
P G
G Q s P o s

 
  

  
    
  
   
  
   
 

 
 
 



Perceptual inference
Policy selection
( , | )
( , | )
( , ) E [ ( , )]
E [ln ( | ) ( | ) ln ( , )]
E [ ( | ) || ( | )] [ ( , ) || ( | ) ( | )]
Q
Q o s
entropy energy
Q o s
expected cost epistemic value(mutual informat
G F
Q o Q s P o s
D Q s P s D Q o s Q s Q o
 
 
    
      
   
 
   

 
 
ion)
Generalised free energy – with some care
( | ) :
( | )
( ) :
( ) :
( | )
( | ) :
P o s t
Q o s
o t
P s t
P s
P s t
 
 





 


 


 




 


© Peter Morgan, May 2019
Active Inference
Karl Friston - UCL
© Peter Morgan, May 2019
ln ( ) ( , )
arg min ( , )
( , ) E [ln ( | ) ln ( , )]
[ ( | ) || ( )] [ [ ( | )]]
Q
expected entropy expected energy
Q
expected cost expected ambiguity
P G
G
G Q s P o s
D Q s P s E H P o s

 
  
   
   
 
  

   

 
 


π
[ ] 0
0
( [ ], [ ]| [ ])
( [ ]) 0
[ ] arg min ( [ ])
( [ ]) E [ln ( [ ]| [ ]) ln ( [ ], [ ])]
[ ( [ ]| [ ]) || ( [ ])]
T
a
T
a
p s a
expected entropy expected energy
expected complexity
d
a d
a p b p b
D p b p

   
  
  
      
    
 

 



I a
a I
I
( [ ]| [ ])
E [ [ ( [ ]| [ ])]]
p a
expected ambiguity
H p b
     

Active states
( , )
s
s f b
 
 
( )
a a
f b F
 
External states
Sensory states
( , )
f b

  
 
prefrontal cortex
β
t
u
VTA/SN
motor cortex
occipital cortex
striatum
t
o
π


s
G hippocampus
Discrete formulation
Dynamic formulation
Expected surprise and free energy
© Peter Morgan, May 2019
What is free-energy?
Free-energy is basically prediction error
where small errors mean low surprise
General Principle – Systems act to minimize uncertainty (their
expected free energy)
sensations – predictions
= prediction error
© Peter Morgan, May 2019
The Markov blanket of cells to brains
Active states
( , , )
a
a f s a 

External states Internal states
Sensory states
( , , )
f s a

 

( , , )
s s
s f s a
 
 
( , , )
f s a
 
  
 
Cell
Brain
© Peter Morgan, May 2019
But what about the Markov blanket?
( , , )
s s a 

( ) ln ( | )
( ) ln ( | )
a
Q p s m
a Q p s m

    
   
Perception
Action
Reinforcement learning, optimal control
and expected utility theory
Infomax, minimum redundancy and the
free-energy principle
Self-organisation, synergetics and
homoeostasis
Bayesian brain, evidence
accumulation and predictive coding
Value
Surprise
Entropy
Model evidence
Pavlov
Haken
Helmholtz
ln ( | )
ln ( | )
[ ln ( | )]
( | )
t
p s m
F p s m
E p s m
p s m

  
 

Barlow
( ) ( ) ln ( | )
f x Q p x m
   
© Peter Morgan, May 2019
Application
© Peter Morgan, May 2019
Summary
• Biological agents resist the second law of thermodynamics
• They must minimize their average surprise (entropy)
• They minimize surprise by suppressing prediction error (free-energy)
• Prediction error can be reduced by changing predictions (perception)
• Prediction error can be reduced by changing sensations (action)
• Perception entails recurrent message passing in the brain to optimise predictions
• Action makes predictions come true (and minimises surprise)
Perception Birdsong and categorization
Simulated lesions
Action Active inference
Goal directed reaching
Policies Control and attractors
The mountain-car problem
© Peter Morgan, May 2019
Building AGI
© Peter Morgan, May 2019
Can we build general intelligence?
• We have the theory – active inference
• We have the algorithms/software
• We have the hardware (ASIC, neuromorphic)
• We have the data sets (Internet plus open data sets)
• Need to build out libraries
• A TensorFlow for general intelligence
• Open source? (Open/closed)
• Apollo Project of our time – “Fourth Revolution”
• Human Brain Project
• Deepmind
• BRAIN project
• Should we build AGI/ASI? – safety, ethics, singularity?
© Peter Morgan, May 2019
Competitive Landscape
Major AI Efforts
Other AGI
Projects
• OpenCog – Ben Goertzel (US)
• Numenta – Jeff Hawkins (US)
• Vicarious – Dileep George (US)
• NNAIsense – Jurgen Schmidhuber (Swiss)
• AGI Innovations – Peter Voss (US)
• GoodAI – Marek Rosa (Czech)
• Curious AI – (Finland)
• Eurisko – Doug Lenat (US)
• SOAR – CMU
• ACT-R – CMU
• Sigma – Paul Rosenbloom – USC
• Plus many more
Implementations & Applications
• BNN Simulation Frameworks – SPM, PyNN, NEST, NEURON, Brian
• Various open source frameworks on GitHub
• Hearing aids - GN Group (DK)
• Order of Magnitude - Christian Kaiser (SV)
• Turing.AI – Our company (London)
© Peter Morgan, May 2019
1. Active Eyes – Adaptive, learning cameras for
‘walk through’ airports and ‘counterless’ stores
2. True NLP – An Active Inference based NLP for home,
retail & commercial applications
Turing.AI - Two main, very broad, product
areas – vision and language (stealth mode)
https://turing-ai.co
© Peter Morgan, May 2019
Conclusions
• Deep Learning (ANN) is lacking many of the characteristics and attributes needed
for a general theory of intelligence
• Active inference is such a theory (A ToE* which includes AGI)
• ANN research groups are now (finally) turning to biology for inspiration
• Bioplausible models are starting to appear
• Some groups are starting to look at active inference
• AGI in five years? Ten years?
• Still have to wait for hardware to mature
• Neuromorphic might be the platform that gets us there
* ToE = Theory of Everything
© Peter Morgan, May 2019
References
© Peter Morgan, May 2019
Neuroscience - Books
• Saxe, G. et al, Brain entropy and human intelligence: A resting-state fMRI study, PLOS One,
Feb 12, 2018
• Sterling, P. and Laughlin, S., Principles of Neural Design, MIT Press, 2017
• Slotnick, S., Cognitive Neuroscience of Memory, Cambridge Univ Press, 2017
• Engel, Friston & Kragic, Eds, The Pragmatic Turn - Toward Action-Oriented Views in
Cognitive Science, MIT Press, 2016
• Marcus G., & J. Freeman, Eds, The Future of the Brain, Princeton, Univ Press, 2015
• Gerstner, W. et al, Neuronal Dynamics, Cambridge Univ Press, 2014
• Kandel, E., Principles of Neural Science, 5th ed, McGraw-Hill, 2012
• Rabinovich, Friston and Varona, Eds, Principles of Brain Dynamics, MIT Press, 2012
• Jones, E. G., Thalamus, Cambridge Univ. Press, 2007
• Dayan, P. and L. Abbott, Theoretical Neuroscience, MIT Press, 2005
© Peter Morgan, May 2019
Neuroscience - Papers
• Crick, F., The recent excitement about neural networks, Nature337, 129–132, 1989
• Rao RP and DH Ballard, Predictive coding in the visual cortex, Nature Neuroscience 2:79–87, 1999
• Izhikevich, E. M., Solving the distal reward problem through linkage of STDP and dopamine
signalling, Cereb. Cortex 17, 2443–2452, 2007
• How the brain constructs the world, 2018 https://medicalxpress.com/news/2018-02-brain-world.html
• Lamme, V. A. F. and Roelfsema, P. R., The distinct modes of vision offered by feedforward and recurrent
processing, Trends Neurosci. 23, 571–579, 2000
• Sherman, S. M., Thalamus plays a central role in ongoing cortical functioning, Nat. Neurosci. 16, 533–
541, 2016
• Harris, K. D. and Shepherd, G. M. G., The neocortical circuit: themes and variations, Nat.
Neurosci. 18, 170–181, 2015
• van Kerkoerle, T. et al, Effects of attention and working memory in the different layers of monkey
primary visual cortex, Nat. Commun. 8, 13804, 2017
• Roelfsema, P.R. and A. Holtmaat, Control of synaptic plasticity in deep cortical networks, Nature
Reviews Neuroscience, 19, pages 166–180, 2018
© Peter Morgan, May 2019
Hardware
• Wang, Z. et al, Fully memristive neural networks for pattern classification with
unsupervised learning, Nature Electronics, 8 Feb, 2018
• Microsoft Research, The Future is Quantum, Jan 17, 2018
https://www.microsoft.com/en-us/research/blog/future-is-quantum-with-dr-krysta-
svore/?OCID=MSR_podcast_ksvore_fb
• Suri, M. Advances in Neuromorphic Hardware, Springer, 2017
• Nanalyze, 12 AI Hardware Startups Building New AI Chips, May 2017
https://www.nanalyze.com/2017/05/12-ai-hardware-startups-new-ai-chips/
• Lacey, G. et al, Deep Learning on FPGAs: Past, Present, and Future, Feb 2016
https://arxiv.org/abs/1602.04283
• Human Brain Project, Silicon Brains https://www.humanbrainproject.eu/en/silicon-
brains/
• Artificial Brains http://www.artificialbrains.com
© Peter Morgan, May 2019
Classical Deep Learning
• Schmidhuber, Jurgen, Deep learning in neural networks: An overview, Neural Networks, 61:85–117, 2015
• Bengio, Yoshua et al, Deep Learning, MIT Press, 2016
• LeCun, Y., Bengio, Y., and Hinton, G., Deep Learning, Nature, v.521, p.436–444, May 2016
http://www.nature.com/nature/journal/v521/n7553/abs/nature14539.html
• Brtiz, D. et al, Massive Exploration of Neural Machine Translation Architectures, Mar 2017
https://arxiv.org/abs/1703.03906
• Liu H. et al, Hierarchical representations for efficient architecture search, 2017
https://arxiv.org/abs/1711.00436
• NIPS 2017 Proceedings https://papers.nips.cc/book/advances-in-neural-information-processing-systems-30-
2017
• Deepmind papers https://deepmind.com/blog/deepmind-papers-nips-2017/
• Jeff Dean, Building Intelligent Systems with Large Scale Deep Learning, TensorFlow slides, Google Brain,
2017
• Rawat, W. and Z. Wang, Deep Convolutional Neural Networks for Image Classification: A Comprehensive
Review, Neural Computation, 29(9), Sept 2017
© Peter Morgan, May 2019
New Ideas in Deep Learning
• Pham H. et al, Efficient Neural Architecture Search via Parameter Sharing, Feb 2018,
https://arxiv.org/abs/1802.03268
• Pearl, Judea, Theoretical Impediments to Machine Learning With Seven Sparks from the Causal
Revolution, Jan 2018, https://arxiv.org/abs/1801.04016
• Marcus, Gary, Deep Learning: A Critical Appraisal, Jan 2018, https://arxiv.org/abs/1801.00631
• Chaudhari, P. and S. Soatto, Stochastic gradient descent performs variational inference, Jan 2018,
https://arxiv.org/abs/1710.11029
• Vidal, R. et al, The Mathematics of Deep Learning, Dec 2017, https://arxiv.org/abs/1712.04741
• Sabour, S. et al, Dynamic Routing Between Capsules, Nov 2017, https://arxiv.org/abs/1710.09829
• Jaderberg, M. et al, Population Based Training of Neural Networks, 28 Nov, 2017,
https://arxiv.org/abs/1711.09846
• Chaudhari, P. and S. Soatto, On the energy landscape of deep networks, Apr 2017,
https://arxiv.org/abs/1511.06485
• Scellier, B. and Y. Bengio, Equilibrium propagation: bridging the gap between energy-based models
and backpropagation, Front. Comp. Neuro. 11, 24, 2017
© Peter Morgan, May 2019
Bio-plausible Deep Learning
• Bengio, Y. et al, Towards Biologically Plausible Deep Learning, Aug 2016
https://arxiv.org/abs/1502.04156
• Marblestone, A.H. et al, Toward an Integration of Deep Learning and Neuroscience, Front
Comput Neurosci., 14 Sept, 2016
• Costa, R.P. et al, Cortical microcircuits as gated-recurrent neural networks, Jan 2018
https://arxiv.org/abs/1711.02448
• Lillicrap T.P. et al, Random synaptic feedback weights support error backpropagation for
deep learning, Nature Communications 7:13276, 2016
• Hassabis, D. et al, Neuroscience-Inspired Artificial Intelligence, Neuron, 95(2), July 2017
• Sacramento, J. et al, Dendritic error backpropagation in deep cortical microcircuits, Dec
2017 https://arxiv.org/abs/1801.00062
• Guerguiev, J. et al, Towards deep learning with segregated dendrites, eLife Neuroscience, 5
Dec, 2017
© Peter Morgan, May 2019
Cognitive Science
• Dissecting artificial intelligence to better understand the human brain, Cognitive Neuroscience
Society, March 25, 2018 https://medicalxpress.com/news/2018-03-artificial-intelligence-human-
brain.html
• Barbey, A., Network Neuroscience Theory of Human Intelligence, Trends in Cognitive Sciences,
22(1), Jan 2018
• Navlakha, B. et al, Network Design and the Brain, Trends in Cognitive Sciences, 22 (1), Jan 2018
• Lake, B. et al, Building Machines That Learn and Think Like People, Nov 2016
https://arxiv.org/abs/1604.00289
• Lake, B., et al, Human-level concept learning through probabilistic program induction, Science,
350(6266) Dec 2015
• Tenenbaum, J.B. et al, How to Grow a Mind: Statistics, Structure, and Abstraction, Science,
331(1279) March 2011
• Trends in Cognitive Sciences, Special Issue: The Genetics of Cognition 15 (9), Sept 2011
• William Bialek publications, Princeton https://www.princeton.edu/~wbialek/categories.html
© Peter Morgan, May 2019
Active Inference
• Friston, K., The free-energy principle: a unified brain theory? Nature Reviews
Neuroscience, 11(2), 2010
• Friston, K., Life as we know it, Journal of the Royal Society Interface, 3 July, 2013
• Friston, K. et al, Active Inference: A Process Theory, Neural Computation, 29(1), Jan 2017
• Friston, K., Consciousness is not a thing, but a process of inference, Aeon, 18 May, 2017
• Kirchoff, M. et al, The Markov blankets of life, Journal of the Royal Society Interface, 17
Jan, 2018
• Frassle, S. et al, A generative model of whole-brain effective connectivity, Neuroimage, 25
May, 2018
• Friston, K. et al, Deep temporal models and active inference, Neuroscience &
Biobehavioral Reviews, May 2018
https://www.researchgate.net/publication/325017738_Deep_temporal_models_and_ac
tive_inference
© Peter Morgan, May 2019
AGI
• Schmidhuber, J., Goedel Machines: Self-Referential Universal Problem Solvers Making Provably
Optimal Self-Improvements, Dec 2006, https://arxiv.org/abs/cs/0309048
• Wolpert, D., Physical limits of inference, Oct 2008, https://arxiv.org/abs/0708.1362
• Veness, J. et al, A Monte Carlo AIXI Approximation, Dec 2010, https://arxiv.org/abs/0909.0801
• Sunehag, P. and M. Hutter, Principles of Solomonoff Induction and AIXI, Nov 2011,
https://arxiv.org/abs/1111.6117
• Hutter, M., One Decade of Universal Artificial Intelligence, Feb 2012,
https://arxiv.org/abs/1202.6153
• Silver, D. et al, Mastering the game of Go without human knowledge, Nature, Vol 550, 19 Oct, 2017
• Goertzel, B., Toward a Formal Model of Cognitive Synergy, Mar 2017,
https://arxiv.org/abs/1703.04361
• Hauser, Hermann, Are Machines Better than Humans? Evening lecture on machine intelligence at
SCI, London, 25 October 2017 https://www.youtube.com/watch?v=SVOMyEeXUow
© Peter Morgan, May 2019
Information Theory
• Tishby, N. & R. Schwartz-Ziv, Opening the Black Box of Deep Neural Networks via
Information, Apr 29, 2017, https://arxiv.org/abs/1703.00810
• Chaitin, G.J., From Philosophy to Program Size, Mar 2013,
https://arxiv.org/abs/math/0303352
• Solomonoff, R.J., Machine Learning — Past and Future, Revision of lecture given at
AI@50, The Dartmouth Artificial Intelligence Conference, July 13-15, 2006
• Publications of A. N. Kolmogorov, Annals of Probability, 17(3), July 1989
• Levin, L. A., Universal Sequential Search Problems, Problems of Information Transmission,
9(3), 1973
• Shannon, C.E., A Mathematical Theory of Communication, Bell System Technical Journal,
27 (3):379–423, July 1948
• AIT https://en.m.wikipedia.org/wiki/Algorithmic_information_theory
© Peter Morgan, May 2019
Classic Papers
• Deutsch, David, The Constructor Theory of Life, Journal of the Royal Society Interface, 12(104), 2016
• Crick F., The recent excitement about neural networks, Nature 337:129–132, 1989
• Rumelhart DE, Hinton GE, Williams RJ, Learning representations by back-propagating errors, Nature
323:533–536, 1986
• Solomonoff, R.J., A Formal Theory of Inductive Inference, Part 1, Information and Control, 7(1), Mar,
1964, http://world.std.com/~rjs/1964pt1.ps
• F. Rosenblatt, A probabilistic model for information storage and organization in the brain, Psych.
Rev. 62, 386-407, 1958
• Turing, A.M., Computing Machinery and Intelligence, Mind 49:433-460, 1950
• Schrodinger, E., What is Life? Based on lectures delivered at Trinity College, Dublin, Feb 1943
http://www.whatislife.ie/downloads/What-is-Life.pdf
• McCulloch, W.S. and W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of
Mathematical Biophysics, 5(4):115–133, 1943
• Kolmogorov, A., On Analytical Methods in the Theory of Probability, Mathematische Annalen,
104(1), 1931
© Peter Morgan, May 2019
Books
• Sutton, R. S. & A.G. Barto, Reinforcement Learning, 2nd ed., MIT Press, 2018
• Goodfellow, I. et al, Deep Learning, Cambridge University Press, 2016
• Li, Ming and Paul Vitanyi, An Introduction to Kolmogorov Complexity and Its
Applications. Springer-Verlag, N.Y., 2008
• Hutter M., Universal Artificial Intelligence, Springer–Verlag, 2004
• MacKay, David, Information theory, inference and learning algorithms, Cambridge
University Press, 2003
• Wolfram, S., A New Kind of Science, Wolfram Media, 2002
• Hebb, D. O. The Organization of Behavior, A Neuropsychological Theory, John Wiley &
Sons, 1949
© Peter Morgan, May 2019
Final Word …
https://www.youtube.com/watch?v=7ottuFZYflg
© Peter Morgan, May 2019
Questions
© Peter Morgan, May 2019

More Related Content

Similar to Towards AGI Berlin - Building AGI, May 2019

Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019
Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019
Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019Schaffhausen Institute of Technology
 
How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?Amazon Web Services
 
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical ScienceAri Berman
 
Arduino, Open Source and The Internet of Things Landscape
Arduino, Open Source and The Internet of Things LandscapeArduino, Open Source and The Internet of Things Landscape
Arduino, Open Source and The Internet of Things LandscapeJustin Grammens
 
Materials discovery through theory, computation, and machine learning
Materials discovery through theory, computation, and machine learningMaterials discovery through theory, computation, and machine learning
Materials discovery through theory, computation, and machine learningAnubhav Jain
 
State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...
State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...
State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...inside-BigData.com
 
Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_Jeffrey Shomaker
 
TensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative modelsTensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative modelsSeldon
 
Implementing AI: Hardware Challenges
Implementing AI: Hardware ChallengesImplementing AI: Hardware Challenges
Implementing AI: Hardware ChallengesKTN
 
Vertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IVVertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IVVertex Holdings
 
Natural language Analysis
Natural language AnalysisNatural language Analysis
Natural language AnalysisRudradeb Mitra
 
The Hitchhiker's Guide to Machine Learning with Python & Apache Spark
The Hitchhiker's Guide to Machine Learning with Python & Apache SparkThe Hitchhiker's Guide to Machine Learning with Python & Apache Spark
The Hitchhiker's Guide to Machine Learning with Python & Apache SparkKrishna Sankar
 
Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙
Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙
Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙Tracy Chen
 
Case study on deep learning
Case study on deep learningCase study on deep learning
Case study on deep learningHarshitBarde
 
Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...
Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...
Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...Facultad de Informática UCM
 
Deep Learning for Stock Prediction
Deep Learning for Stock PredictionDeep Learning for Stock Prediction
Deep Learning for Stock PredictionLim Zhi Yuan (Zane)
 
Understanding Jupyter notebooks using bioinformatics examples
Understanding Jupyter notebooks using bioinformatics examplesUnderstanding Jupyter notebooks using bioinformatics examples
Understanding Jupyter notebooks using bioinformatics examplesLynn Langit
 

Similar to Towards AGI Berlin - Building AGI, May 2019 (20)

Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019
Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019
Serguei “SB” Beloussov - Future Of Computing at SIT Insights in Technology 2019
 
How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?How Can We Answer the Really BIG Questions?
How Can We Answer the Really BIG Questions?
 
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
 
Arduino, Open Source and The Internet of Things Landscape
Arduino, Open Source and The Internet of Things LandscapeArduino, Open Source and The Internet of Things Landscape
Arduino, Open Source and The Internet of Things Landscape
 
Materials discovery through theory, computation, and machine learning
Materials discovery through theory, computation, and machine learningMaterials discovery through theory, computation, and machine learning
Materials discovery through theory, computation, and machine learning
 
State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...
State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...
State-Of-The Art Machine Learning Algorithms and How They Are Affected By Nea...
 
Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_
 
TensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative modelsTensorFlow London: Cutting edge generative models
TensorFlow London: Cutting edge generative models
 
Implementing AI: Hardware Challenges
Implementing AI: Hardware ChallengesImplementing AI: Hardware Challenges
Implementing AI: Hardware Challenges
 
Blue Brain Project
Blue Brain ProjectBlue Brain Project
Blue Brain Project
 
Vertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IVVertex Perspectives | AI Optimized Chipsets | Part IV
Vertex Perspectives | AI Optimized Chipsets | Part IV
 
GSU-RF-2013-Reddy-3
GSU-RF-2013-Reddy-3GSU-RF-2013-Reddy-3
GSU-RF-2013-Reddy-3
 
Natural language Analysis
Natural language AnalysisNatural language Analysis
Natural language Analysis
 
The Hitchhiker's Guide to Machine Learning with Python & Apache Spark
The Hitchhiker's Guide to Machine Learning with Python & Apache SparkThe Hitchhiker's Guide to Machine Learning with Python & Apache Spark
The Hitchhiker's Guide to Machine Learning with Python & Apache Spark
 
Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙
Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙
Cloud Computing,雲端運算-中研院網格計畫主持人林誠謙
 
Case study on deep learning
Case study on deep learningCase study on deep learning
Case study on deep learning
 
Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...
Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...
Cognitive Computers: The Next Wave of Computing Innovation - Prof. Antonio Go...
 
1. GRID COMPUTING
1. GRID COMPUTING1. GRID COMPUTING
1. GRID COMPUTING
 
Deep Learning for Stock Prediction
Deep Learning for Stock PredictionDeep Learning for Stock Prediction
Deep Learning for Stock Prediction
 
Understanding Jupyter notebooks using bioinformatics examples
Understanding Jupyter notebooks using bioinformatics examplesUnderstanding Jupyter notebooks using bioinformatics examples
Understanding Jupyter notebooks using bioinformatics examples
 

More from Peter Morgan

AI in Physics - University of Washington, Jan 2024
AI in Physics - University of Washington, Jan 2024AI in Physics - University of Washington, Jan 2024
AI in Physics - University of Washington, Jan 2024Peter Morgan
 
Simulation Hypothesis 2017
Simulation Hypothesis 2017Simulation Hypothesis 2017
Simulation Hypothesis 2017Peter Morgan
 
AI Developments Aug 2017
AI Developments Aug 2017AI Developments Aug 2017
AI Developments Aug 2017Peter Morgan
 
London Exponential Technologies Meetup, July 2017
London Exponential Technologies Meetup, July 2017London Exponential Technologies Meetup, July 2017
London Exponential Technologies Meetup, July 2017Peter Morgan
 
Robotics Overview 2016
Robotics Overview 2016Robotics Overview 2016
Robotics Overview 2016Peter Morgan
 
AI and Blockchain 2017
AI and Blockchain 2017AI and Blockchain 2017
AI and Blockchain 2017Peter Morgan
 
AI in Healthcare 2017
AI in Healthcare 2017AI in Healthcare 2017
AI in Healthcare 2017Peter Morgan
 
AI Predictions 2017
AI Predictions 2017AI Predictions 2017
AI Predictions 2017Peter Morgan
 
AI State of Play Dec 2016 NYC
AI State of Play Dec 2016 NYCAI State of Play Dec 2016 NYC
AI State of Play Dec 2016 NYCPeter Morgan
 
Big data – An Introduction, July 2013
Big data – An Introduction, July 2013Big data – An Introduction, July 2013
Big data – An Introduction, July 2013Peter Morgan
 
Machine Learning - Where to Next?, May 2015
Machine Learning  - Where to Next?, May 2015Machine Learning  - Where to Next?, May 2015
Machine Learning - Where to Next?, May 2015Peter Morgan
 

More from Peter Morgan (11)

AI in Physics - University of Washington, Jan 2024
AI in Physics - University of Washington, Jan 2024AI in Physics - University of Washington, Jan 2024
AI in Physics - University of Washington, Jan 2024
 
Simulation Hypothesis 2017
Simulation Hypothesis 2017Simulation Hypothesis 2017
Simulation Hypothesis 2017
 
AI Developments Aug 2017
AI Developments Aug 2017AI Developments Aug 2017
AI Developments Aug 2017
 
London Exponential Technologies Meetup, July 2017
London Exponential Technologies Meetup, July 2017London Exponential Technologies Meetup, July 2017
London Exponential Technologies Meetup, July 2017
 
Robotics Overview 2016
Robotics Overview 2016Robotics Overview 2016
Robotics Overview 2016
 
AI and Blockchain 2017
AI and Blockchain 2017AI and Blockchain 2017
AI and Blockchain 2017
 
AI in Healthcare 2017
AI in Healthcare 2017AI in Healthcare 2017
AI in Healthcare 2017
 
AI Predictions 2017
AI Predictions 2017AI Predictions 2017
AI Predictions 2017
 
AI State of Play Dec 2016 NYC
AI State of Play Dec 2016 NYCAI State of Play Dec 2016 NYC
AI State of Play Dec 2016 NYC
 
Big data – An Introduction, July 2013
Big data – An Introduction, July 2013Big data – An Introduction, July 2013
Big data – An Introduction, July 2013
 
Machine Learning - Where to Next?, May 2015
Machine Learning  - Where to Next?, May 2015Machine Learning  - Where to Next?, May 2015
Machine Learning - Where to Next?, May 2015
 

Recently uploaded

Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsPrecisely
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 

Recently uploaded (20)

Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power Systems
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 

Towards AGI Berlin - Building AGI, May 2019

  • 3. Outline of Talk • Physical Systems • Biological • Non-biological • Deep Learning • Description • Types • Reinforcement Learning • Latest Research • Towards AGI • Overview • Comparisons • Building AGI • Conclusions © Peter Morgan, May 2019
  • 4. Motivation • Solve (general) intelligence • Use it to solve everything else • Medicine • Cancer • Brain disease (Alzheimer's, etc.) • Longevity • Physics • Maths • Materials science • Social © Peter Morgan, May 2019
  • 5. What is Intelligence? © Peter Morgan, May 2019
  • 6. © Peter Morgan, May 2019
  • 7. How will we get there? Physics Computer Science Neuroscience © Peter Morgan, May 2019 It takes a village to create an AGI Psychology
  • 8. Physical Systems • Biological • Plants, bacteria, insects, reptiles, mammalian, biological brains • Classical (non-biological) • CPU - Intel Xeon SP, AMD RyZen, Qualcomm, IBM PowerPC, ARM • GPU - Nvidia (Volta), AMD (Vega) • FPGA - Intel (Altera, Xylinx etc.) • ASIC - Google TPU, Graphcore IPU, Intel Nervana, Wave, … • Neuromorphic (Human Brain Project - SpiNNaker, BrainScaleS; IBM TrueNorth; Intel Liohi, … • Quantum • IBM, Microsoft, Intel, Google, DWave, Rigetti, … • Quantum biology? (photosynthesis, navigation, …) • QuantumML, Quantum Intelligence © Peter Morgan, May 2019
  • 9. Types of Physical Computation Systems* *Can we find a theory that unifies them all (classical, quantum, biological, non-biological) Digital Neuromorphic Quantum Biological © Peter Morgan, May 2019
  • 14. Hand drawn neuron types From "Structure of the Mammalian Retina" c.1900, by Santiago Ramon y Cajal. © Peter Morgan, May 2019
  • 16. © Peter Morgan, May 2019
  • 17. Cortical columns in the cortex © Peter Morgan, May 2019
  • 18. © Peter Morgan, May 2019
  • 23. Non-biological Hardware • Digital • CPU • GPU • FPGA • ASIC • Neuromorphic • Various architectures • SpiNNaker, BrainScaleS, TrueNorth, … • Quantum • Different qubits • Anyons, superconducting, photonic, … © Peter Morgan, May 2019
  • 24. Digital Computing • Abacus • Charles Babbage • Ada Lovelace • Vacuum tubes (valves) • Turing • Von Neumann • ENIAC • Transistor (Bardeen, Brattain, Shockey, 1947) • Intel • ARM • Nvidia • ASICs © Peter Morgan, May 2019
  • 25. © Peter Morgan, May 2019
  • 27. CPU – Intel Xeon Up to 32 cores, ~1 TFlops © Peter Morgan, May 2019
  • 28. GPU – Nvidia Volta V100 21 billion transistors, 120 TFlops © Peter Morgan, May 2019
  • 29. DGX-2 - released Mar 2018 16 V100’s, 2 PFlops, 30TB storage ($400k) 2 PFlops! © Peter Morgan, May 2019
  • 30. ASIC – Google TPU 3.0 © Peter Morgan, May 2019 360 TFlops! - Announced Google I/O, May 2018
  • 31. ASIC - Graphcore IPU © Peter Morgan, May 2019 >200 TFlops
  • 32. © Peter Morgan, May 2019
  • 33. Cloud TPU’s © Peter Morgan, May 2019 Over 100 PetaFlops !
  • 34. Summit US IBM AC922 system 4,608 servers Each server contains two 22-core IBM Power9 CPUs six Nvidia Tesla V100 GPUs  200PFlops (3 ExaFlops mixed precision!) 2 tennis courts area 250 Petabytes storage 13MW power $200million Announced 5 June 2018 © Peter Morgan, May 2019
  • 35. HPC – what’s next? Currently 200PFlops - Summit By 2020 – beyond Exascale © Peter Morgan, May 2019
  • 37. Aurora 21 © Peter Morgan, May 2019 Exascale compute by 2021, Argonne National Lab, Intel + Cray © Peter Morgan, June 14 2018
  • 39. Biology vs Digital © Peter Morgan, May 2019
  • 40. Neuromorphic Computing • Biologically inspired • First proposed Carver Mead, Caltech, 1980’s • Uses analogue signals – spiking neural networks (SNN) • SpiNNaker (Manchester, HBP, Furber) • BrainScaleS (Heidelberg, HBP, Schemmel) • TrueNorth (IBM, Modha) • Intel Liohi • Startups (Knowm, Spaun, etc.) • Up to 1 million cores, 1 billion “neurons” (mouse) • Need to scale 100X  human brain • Relatively low power • Available on the (HBP) cloud today © Peter Morgan, May 2019
  • 44. © Peter Morgan, May 2019
  • 45. Neuromorphic v ASIC Analogue v Digital © Peter Morgan, May 2019
  • 46. Quantum Computing • First proposed by Richard Feynman, Caltech, 1980’s • Qubits – spin 1, 0 and superposition states (QM) • (Nature is) fundamentally probabilistic at atomic scale • Have to be kept cold (mKelvin) to avoid noise/decoherence • Building is an engineering problem (theory is known) • Several approaches - superconductors, trapped ions, semiconductors, topological structures • Several initiatives (with access available) • Microsoft, IBM, Google, Intel, Dwave, Rigetti, etc. • Can login today • Many applications – optimization, cryptography, drug discovery, etc. © Peter Morgan, May 2019
  • 47. IBM 50 Qubit Quantum Computer © Peter Morgan, May 2019
  • 48. © Peter Morgan, May 2019
  • 49. Quantum Logic Gates © Peter Morgan, May 2019
  • 50. Summary – Now have three non-biological stacks Algorithms Distributed Layer OS Hardware Classical Neuromorphic Quantum © Peter Morgan, May 2019
  • 51. © Peter Morgan, May 2019
  • 52. Outline • Physical Systems • Biological • Non-biological • Deep Learning • Description • Types • Reinforcement Learning • Latest Research in DL • Towards AGI? • Overview • Comparisons • AGI • Conclusions © Peter Morgan, May 2019
  • 53. Early papers © Peter Morgan, May 2019
  • 54. Nodes and Layers © Peter Morgan, May 2019
  • 55. © Peter Morgan, May 2019
  • 56. More Neural Networks (“Neural Network Zoo”) © Peter Morgan, May 2019
  • 57. Computation in each node © Peter Morgan, May 2019
  • 58. Universal Approximation Theorem • A feed-forward network with a single hidden layer containing a finite number of neurons, can approximate continuous functions in Rn, under mild assumptions on the activation function • We can define as an approximate realization of f(x): • One of the first versions of the theorem was proved by George Cybenko in 1989 for sigmoid activation functions • Kurt Hornik showed in 1991 that it is not the specific choice of the activation function, but rather the multilayer feedforward architecture which gives neural networks the potential of being universal approximators • Cybenko, G., Approximations by superpositions of sigmoidal functions, Mathematics of Control, Signals, and Systems, 2(4), 303-314, 1989 • Kurt Hornik (1991) Approximation Capabilities of Multilayer Feedforward Networks, Neural Networks, 4(2), 251–257, 1991 © Peter Morgan, May 2019
  • 60. Hyperparameters • Activation function • Optimizations • Loss (cost) function • Learning rate • Initialization • Batch normalization • Automation • Hyperparameter tuning • AutoML • https://research.googleblog.com/2018/03/using-machine-learning-to-discover.html © Peter Morgan, May 2019
  • 62. Deep Learning Performance ImageNet Error rate is now around 2.2%, less than half that of average humans © Peter Morgan, May 2019
  • 63. Convolutional Neural Networks • First developed in 1970’s. • Widely used for image recognition and classification. • Inspired by biological processes, CNN’s are a type of feed-forward ANN. • The individual neurons are tiled in such a way that they respond to overlapping regions in the visual field • Yann LeCun – Bell Labs, 90’s © Peter Morgan, May 2019
  • 64. Recurrent Neural Networks • First developed in 1970’s. • RNN’s are neural networks that are used to predict the next element in a sequence or time series. • This could be, for example, words in a sentence or letters in a word. • Applications include predicting or generating music, stories, news, code, financial instrument pricing, text, speech, in fact the next element in any event stream. © Peter Morgan, May 2019
  • 65. GANs Generative Adversarial Networks - introduced by Ian Goodfellow et al in 2014 (see references) A class of artificial intelligence algorithms used in unsupervised deep learning A theory of adversarial examples, resembling what we have for normal supervised learning Implemented by a system of two neural networks, a discriminator, D and a generator, G D & G contest with each other in a zero-sum game framework Generator generates candidate networks and the discriminator evaluates them © Peter Morgan, May 2019
  • 66. Stacked Generative Adversarial Networks https://arxiv.org/abs/1612.04357v1 © Peter Morgan, May 2019
  • 67. NN Models AlexNet (Toronto) VGG (Oxford) ResNet (Microsoft) Inception (Google) DenseNet (Cornell) SqueezNet (Berkeley) MobileNet (Google) NASNet (Google) And many (hundreds) more ... © Peter Morgan, May 2019
  • 69. Top 20 ML/DL Frameworks KD Nuggets Feb 2018 https://www.kdnuggets.com/2018/02/top-20-python-ai-machine-learning-open-source-projects.html * Deep Learning o Machine Learning * MXNet *CNTK © Peter Morgan, May 2019
  • 70. TensorFlow • TensorFlow is the open sourced deep learning library from Google (Nov 2015) • It is their second generation system for the implementation and deployment of large-scale machine learning models • Written in C++ with a python interface, originated from research and deploying machine learning projects throughout a wide range of Google products and services • Initially TF ran only on a single node (your laptop, say), but now runs on distributed clusters • Available across all the major cloud providers (TFaaS) • Second most popular framework on GitHub • Over 100,000 stars as of May 2018 • https://www.tensorflow.org/ © Peter Morgan, May 2019
  • 71. TensorFlow supports many platforms RaspberryPi Android iOS TPU GPU CPU CloudTPU © Peter Morgan, May 2019
  • 72. Growth of Deep Learning atGoogle and many more . . .. Directories containing model descriptionfiles © Peter Morgan, May 2019
  • 73. TensorFlow Popularity © Peter Morgan, May 2019
  • 74. Other Frameworks • CNTK (Microsoft) • MXnet (Amazon) • Keras (Open source community) • PyTorch (Facebook) • Neon (Intel) • Chainer (Preferred Networks) © Peter Morgan, May 2019
  • 75. Data Sets • Text, speech, images, video, time series • Examples - MNIST and Labeled Faces in the Wild (LFW). MNIST LFW © Peter Morgan, May 2019
  • 76. Open Source • ML Frameworks – open source (e.g., TensorFlow) • Operating systems – open source (Linux) • Hardware – open source (OCP = Open Compute Project) • Data sets – open source (see previous slide) • Research – open source (see arXiv) • The fourth industrial revolution will be (is) open source © Peter Morgan, May 2019
  • 77. Reinforcement Learning • Goal driven • Reward and penalty • TD Learning • DQN • AlphaGo • Latest research • http://metalearning-symposium.ml © Peter Morgan, May 2019
  • 78. RL Research Directions • Deep Reinforcement Learning Symposium, NIPS 2017 • https://sites.google.com/view/deeprl-symposium- nips2017/home • Berkeley (BAIR) http://bair.berkeley.edu • Peter Abdeel • Serge Levine • Deepmind https://deepmind.com • IMPALA (DMLab) https://deepmind.com/blog/impala-scalable- distributed-deeprl-dmlab-30/ • OpenAI https://openai.com • Research white papers • Graphcore - Bristol ASIC company • https://www.graphcore.ai/posts/directions-of-ai- research © Peter Morgan, May 2019
  • 79. Outline • Physical Systems • Biological • Non-biological • Deep Learning • Description • Types • Reinforcement Learning • Latest Research in DL • Towards AGI • Overview • Comparisons • Building AGI • Conclusions © Peter Morgan, May 2019
  • 80. Towards AGI • What do we need? • Active Inference • Other approaches • Applications • Building AGI AGI = Artificial General Intelligence © Peter Morgan, May 2019
  • 81. © Peter Morgan, May 2019
  • 82. © Peter Morgan, May 2019
  • 83. © Peter Morgan, May 2019
  • 84. © Peter Morgan, May 2019
  • 85. Comparisons - ANN vs BNN • Neural circuits in the brain develop via synaptic pruning; a process by which connections are overproduced and then eliminated over time • In contrast, computer scientists typically design networks by starting with an initially sparse topology and gradually adding connections • AI (specific) vs AGI (general) • Yann LeCun – CNN’s Bell Labs in ’80/90’s – “mathematical, not biological” • Gone as far as we can with ”just” mathematics • Now almost every researcher looking to biology for inspiration • Costa et al, 2018, etc. (see “Bio-plausible Deep Learning” in reference section) ANN = Artificial Neural Networks BNN = Biological Neural Networks © Peter Morgan, May 2019
  • 86. Approaches to AGI • Helmholtz (Late 1800’s) • Friston – Active Inference • Tishby – Information bottleneck • Bialek – Biophysics • Hutter - AIXI • Schmidhuber – Godel Machine • Etc. © Peter Morgan, May 2019
  • 87. Active Inference • Free Energy Principle • Systems act to minimize their expected free energy • Reduce uncertainty (or surprisal) • F = Complexity – Accuracy • Prediction error = expected outcome – actual outcome = surprise • Theory of Everything (ToE) • In physics - try to unify gravity and quantum mechanics  call this a ToE • But actually Active Inference is more encompassing than even this • It encompasses all interactions and dynamics (physical phenomena) • Over all time scales • Over all distance scales • Also see Constructor Theory • David Deutsch (Oxford) © Peter Morgan, May 2019
  • 88. What are the principles? Newtonian mechanics – three laws Special relativity – invariance of laws under a Lorentz transformation GR – Principle of Equivalence Electromagnetism – Maxwell’s equations Thermodynamics – three laws Quantum mechanics – uncertainty principle Relativistic QM – Dirac equation Dark energy/dark matter – we don’t know yet All of the above = Principle of Least Action © Peter Morgan, May 2019
  • 90. Analogy – Einstein’s General Theory of Relativity • Made some very general (and insightful) assumptions about the laws of physics in a gravitational field (non-inertial frames) • Equivalence principle • Covariance of laws of physics • Generalised coordinate system – Riemannian geometry • Spacetime is curved • Standing on the shoulders of giants • After ten years of hard work he finally wrote down his now famous field equations © Peter Morgan, May 2019
  • 91. All known physics – Field theoretic © Peter Morgan, May 2019
  • 92. Active Inference - Information theoretic (uses generalised free energy) ( ) argmin E [ ( , )] [ ( ) || ( )] ( ) argmin ( , ) ( , ) E [ln ( | ) ln ( , | )] ln ( ) ( , ) ( , ) E [ln ( | ) ln ( , | )] Q Q entropy energy Q entropy energy Q F D Q P Q s F F Q s P o s P G G Q s P o s                                          Perceptual inference Policy selection ( , | ) ( , | ) ( , ) E [ ( , )] E [ln ( | ) ( | ) ln ( , )] E [ ( | ) || ( | )] [ ( , ) || ( | ) ( | )] Q Q o s entropy energy Q o s expected cost epistemic value(mutual informat G F Q o Q s P o s D Q s P s D Q o s Q s Q o                                ion) Generalised free energy – with some care ( | ) : ( | ) ( ) : ( ) : ( | ) ( | ) : P o s t Q o s o t P s t P s P s t                            © Peter Morgan, May 2019
  • 93. Active Inference Karl Friston - UCL © Peter Morgan, May 2019
  • 94. ln ( ) ( , ) arg min ( , ) ( , ) E [ln ( | ) ln ( , )] [ ( | ) || ( )] [ [ ( | )]] Q expected entropy expected energy Q expected cost expected ambiguity P G G G Q s P o s D Q s P s E H P o s                                π [ ] 0 0 ( [ ], [ ]| [ ]) ( [ ]) 0 [ ] arg min ( [ ]) ( [ ]) E [ln ( [ ]| [ ]) ln ( [ ], [ ])] [ ( [ ]| [ ]) || ( [ ])] T a T a p s a expected entropy expected energy expected complexity d a d a p b p b D p b p                                I a a I I ( [ ]| [ ]) E [ [ ( [ ]| [ ])]] p a expected ambiguity H p b        Active states ( , ) s s f b     ( ) a a f b F   External states Sensory states ( , ) f b       prefrontal cortex β t u VTA/SN motor cortex occipital cortex striatum t o π   s G hippocampus Discrete formulation Dynamic formulation Expected surprise and free energy © Peter Morgan, May 2019
  • 95. What is free-energy? Free-energy is basically prediction error where small errors mean low surprise General Principle – Systems act to minimize uncertainty (their expected free energy) sensations – predictions = prediction error © Peter Morgan, May 2019
  • 96. The Markov blanket of cells to brains Active states ( , , ) a a f s a   External states Internal states Sensory states ( , , ) f s a     ( , , ) s s s f s a     ( , , ) f s a        Cell Brain © Peter Morgan, May 2019
  • 97. But what about the Markov blanket? ( , , ) s s a   ( ) ln ( | ) ( ) ln ( | ) a Q p s m a Q p s m           Perception Action Reinforcement learning, optimal control and expected utility theory Infomax, minimum redundancy and the free-energy principle Self-organisation, synergetics and homoeostasis Bayesian brain, evidence accumulation and predictive coding Value Surprise Entropy Model evidence Pavlov Haken Helmholtz ln ( | ) ln ( | ) [ ln ( | )] ( | ) t p s m F p s m E p s m p s m        Barlow ( ) ( ) ln ( | ) f x Q p x m     © Peter Morgan, May 2019
  • 99. Summary • Biological agents resist the second law of thermodynamics • They must minimize their average surprise (entropy) • They minimize surprise by suppressing prediction error (free-energy) • Prediction error can be reduced by changing predictions (perception) • Prediction error can be reduced by changing sensations (action) • Perception entails recurrent message passing in the brain to optimise predictions • Action makes predictions come true (and minimises surprise) Perception Birdsong and categorization Simulated lesions Action Active inference Goal directed reaching Policies Control and attractors The mountain-car problem © Peter Morgan, May 2019
  • 100. Building AGI © Peter Morgan, May 2019
  • 101. Can we build general intelligence? • We have the theory – active inference • We have the algorithms/software • We have the hardware (ASIC, neuromorphic) • We have the data sets (Internet plus open data sets) • Need to build out libraries • A TensorFlow for general intelligence • Open source? (Open/closed) • Apollo Project of our time – “Fourth Revolution” • Human Brain Project • Deepmind • BRAIN project • Should we build AGI/ASI? – safety, ethics, singularity? © Peter Morgan, May 2019
  • 103. Other AGI Projects • OpenCog – Ben Goertzel (US) • Numenta – Jeff Hawkins (US) • Vicarious – Dileep George (US) • NNAIsense – Jurgen Schmidhuber (Swiss) • AGI Innovations – Peter Voss (US) • GoodAI – Marek Rosa (Czech) • Curious AI – (Finland) • Eurisko – Doug Lenat (US) • SOAR – CMU • ACT-R – CMU • Sigma – Paul Rosenbloom – USC • Plus many more
  • 104. Implementations & Applications • BNN Simulation Frameworks – SPM, PyNN, NEST, NEURON, Brian • Various open source frameworks on GitHub • Hearing aids - GN Group (DK) • Order of Magnitude - Christian Kaiser (SV) • Turing.AI – Our company (London) © Peter Morgan, May 2019
  • 105. 1. Active Eyes – Adaptive, learning cameras for ‘walk through’ airports and ‘counterless’ stores 2. True NLP – An Active Inference based NLP for home, retail & commercial applications Turing.AI - Two main, very broad, product areas – vision and language (stealth mode) https://turing-ai.co © Peter Morgan, May 2019
  • 106. Conclusions • Deep Learning (ANN) is lacking many of the characteristics and attributes needed for a general theory of intelligence • Active inference is such a theory (A ToE* which includes AGI) • ANN research groups are now (finally) turning to biology for inspiration • Bioplausible models are starting to appear • Some groups are starting to look at active inference • AGI in five years? Ten years? • Still have to wait for hardware to mature • Neuromorphic might be the platform that gets us there * ToE = Theory of Everything © Peter Morgan, May 2019
  • 108. Neuroscience - Books • Saxe, G. et al, Brain entropy and human intelligence: A resting-state fMRI study, PLOS One, Feb 12, 2018 • Sterling, P. and Laughlin, S., Principles of Neural Design, MIT Press, 2017 • Slotnick, S., Cognitive Neuroscience of Memory, Cambridge Univ Press, 2017 • Engel, Friston & Kragic, Eds, The Pragmatic Turn - Toward Action-Oriented Views in Cognitive Science, MIT Press, 2016 • Marcus G., & J. Freeman, Eds, The Future of the Brain, Princeton, Univ Press, 2015 • Gerstner, W. et al, Neuronal Dynamics, Cambridge Univ Press, 2014 • Kandel, E., Principles of Neural Science, 5th ed, McGraw-Hill, 2012 • Rabinovich, Friston and Varona, Eds, Principles of Brain Dynamics, MIT Press, 2012 • Jones, E. G., Thalamus, Cambridge Univ. Press, 2007 • Dayan, P. and L. Abbott, Theoretical Neuroscience, MIT Press, 2005 © Peter Morgan, May 2019
  • 109. Neuroscience - Papers • Crick, F., The recent excitement about neural networks, Nature337, 129–132, 1989 • Rao RP and DH Ballard, Predictive coding in the visual cortex, Nature Neuroscience 2:79–87, 1999 • Izhikevich, E. M., Solving the distal reward problem through linkage of STDP and dopamine signalling, Cereb. Cortex 17, 2443–2452, 2007 • How the brain constructs the world, 2018 https://medicalxpress.com/news/2018-02-brain-world.html • Lamme, V. A. F. and Roelfsema, P. R., The distinct modes of vision offered by feedforward and recurrent processing, Trends Neurosci. 23, 571–579, 2000 • Sherman, S. M., Thalamus plays a central role in ongoing cortical functioning, Nat. Neurosci. 16, 533– 541, 2016 • Harris, K. D. and Shepherd, G. M. G., The neocortical circuit: themes and variations, Nat. Neurosci. 18, 170–181, 2015 • van Kerkoerle, T. et al, Effects of attention and working memory in the different layers of monkey primary visual cortex, Nat. Commun. 8, 13804, 2017 • Roelfsema, P.R. and A. Holtmaat, Control of synaptic plasticity in deep cortical networks, Nature Reviews Neuroscience, 19, pages 166–180, 2018 © Peter Morgan, May 2019
  • 110. Hardware • Wang, Z. et al, Fully memristive neural networks for pattern classification with unsupervised learning, Nature Electronics, 8 Feb, 2018 • Microsoft Research, The Future is Quantum, Jan 17, 2018 https://www.microsoft.com/en-us/research/blog/future-is-quantum-with-dr-krysta- svore/?OCID=MSR_podcast_ksvore_fb • Suri, M. Advances in Neuromorphic Hardware, Springer, 2017 • Nanalyze, 12 AI Hardware Startups Building New AI Chips, May 2017 https://www.nanalyze.com/2017/05/12-ai-hardware-startups-new-ai-chips/ • Lacey, G. et al, Deep Learning on FPGAs: Past, Present, and Future, Feb 2016 https://arxiv.org/abs/1602.04283 • Human Brain Project, Silicon Brains https://www.humanbrainproject.eu/en/silicon- brains/ • Artificial Brains http://www.artificialbrains.com © Peter Morgan, May 2019
  • 111. Classical Deep Learning • Schmidhuber, Jurgen, Deep learning in neural networks: An overview, Neural Networks, 61:85–117, 2015 • Bengio, Yoshua et al, Deep Learning, MIT Press, 2016 • LeCun, Y., Bengio, Y., and Hinton, G., Deep Learning, Nature, v.521, p.436–444, May 2016 http://www.nature.com/nature/journal/v521/n7553/abs/nature14539.html • Brtiz, D. et al, Massive Exploration of Neural Machine Translation Architectures, Mar 2017 https://arxiv.org/abs/1703.03906 • Liu H. et al, Hierarchical representations for efficient architecture search, 2017 https://arxiv.org/abs/1711.00436 • NIPS 2017 Proceedings https://papers.nips.cc/book/advances-in-neural-information-processing-systems-30- 2017 • Deepmind papers https://deepmind.com/blog/deepmind-papers-nips-2017/ • Jeff Dean, Building Intelligent Systems with Large Scale Deep Learning, TensorFlow slides, Google Brain, 2017 • Rawat, W. and Z. Wang, Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review, Neural Computation, 29(9), Sept 2017 © Peter Morgan, May 2019
  • 112. New Ideas in Deep Learning • Pham H. et al, Efficient Neural Architecture Search via Parameter Sharing, Feb 2018, https://arxiv.org/abs/1802.03268 • Pearl, Judea, Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution, Jan 2018, https://arxiv.org/abs/1801.04016 • Marcus, Gary, Deep Learning: A Critical Appraisal, Jan 2018, https://arxiv.org/abs/1801.00631 • Chaudhari, P. and S. Soatto, Stochastic gradient descent performs variational inference, Jan 2018, https://arxiv.org/abs/1710.11029 • Vidal, R. et al, The Mathematics of Deep Learning, Dec 2017, https://arxiv.org/abs/1712.04741 • Sabour, S. et al, Dynamic Routing Between Capsules, Nov 2017, https://arxiv.org/abs/1710.09829 • Jaderberg, M. et al, Population Based Training of Neural Networks, 28 Nov, 2017, https://arxiv.org/abs/1711.09846 • Chaudhari, P. and S. Soatto, On the energy landscape of deep networks, Apr 2017, https://arxiv.org/abs/1511.06485 • Scellier, B. and Y. Bengio, Equilibrium propagation: bridging the gap between energy-based models and backpropagation, Front. Comp. Neuro. 11, 24, 2017 © Peter Morgan, May 2019
  • 113. Bio-plausible Deep Learning • Bengio, Y. et al, Towards Biologically Plausible Deep Learning, Aug 2016 https://arxiv.org/abs/1502.04156 • Marblestone, A.H. et al, Toward an Integration of Deep Learning and Neuroscience, Front Comput Neurosci., 14 Sept, 2016 • Costa, R.P. et al, Cortical microcircuits as gated-recurrent neural networks, Jan 2018 https://arxiv.org/abs/1711.02448 • Lillicrap T.P. et al, Random synaptic feedback weights support error backpropagation for deep learning, Nature Communications 7:13276, 2016 • Hassabis, D. et al, Neuroscience-Inspired Artificial Intelligence, Neuron, 95(2), July 2017 • Sacramento, J. et al, Dendritic error backpropagation in deep cortical microcircuits, Dec 2017 https://arxiv.org/abs/1801.00062 • Guerguiev, J. et al, Towards deep learning with segregated dendrites, eLife Neuroscience, 5 Dec, 2017 © Peter Morgan, May 2019
  • 114. Cognitive Science • Dissecting artificial intelligence to better understand the human brain, Cognitive Neuroscience Society, March 25, 2018 https://medicalxpress.com/news/2018-03-artificial-intelligence-human- brain.html • Barbey, A., Network Neuroscience Theory of Human Intelligence, Trends in Cognitive Sciences, 22(1), Jan 2018 • Navlakha, B. et al, Network Design and the Brain, Trends in Cognitive Sciences, 22 (1), Jan 2018 • Lake, B. et al, Building Machines That Learn and Think Like People, Nov 2016 https://arxiv.org/abs/1604.00289 • Lake, B., et al, Human-level concept learning through probabilistic program induction, Science, 350(6266) Dec 2015 • Tenenbaum, J.B. et al, How to Grow a Mind: Statistics, Structure, and Abstraction, Science, 331(1279) March 2011 • Trends in Cognitive Sciences, Special Issue: The Genetics of Cognition 15 (9), Sept 2011 • William Bialek publications, Princeton https://www.princeton.edu/~wbialek/categories.html © Peter Morgan, May 2019
  • 115. Active Inference • Friston, K., The free-energy principle: a unified brain theory? Nature Reviews Neuroscience, 11(2), 2010 • Friston, K., Life as we know it, Journal of the Royal Society Interface, 3 July, 2013 • Friston, K. et al, Active Inference: A Process Theory, Neural Computation, 29(1), Jan 2017 • Friston, K., Consciousness is not a thing, but a process of inference, Aeon, 18 May, 2017 • Kirchoff, M. et al, The Markov blankets of life, Journal of the Royal Society Interface, 17 Jan, 2018 • Frassle, S. et al, A generative model of whole-brain effective connectivity, Neuroimage, 25 May, 2018 • Friston, K. et al, Deep temporal models and active inference, Neuroscience & Biobehavioral Reviews, May 2018 https://www.researchgate.net/publication/325017738_Deep_temporal_models_and_ac tive_inference © Peter Morgan, May 2019
  • 116. AGI • Schmidhuber, J., Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements, Dec 2006, https://arxiv.org/abs/cs/0309048 • Wolpert, D., Physical limits of inference, Oct 2008, https://arxiv.org/abs/0708.1362 • Veness, J. et al, A Monte Carlo AIXI Approximation, Dec 2010, https://arxiv.org/abs/0909.0801 • Sunehag, P. and M. Hutter, Principles of Solomonoff Induction and AIXI, Nov 2011, https://arxiv.org/abs/1111.6117 • Hutter, M., One Decade of Universal Artificial Intelligence, Feb 2012, https://arxiv.org/abs/1202.6153 • Silver, D. et al, Mastering the game of Go without human knowledge, Nature, Vol 550, 19 Oct, 2017 • Goertzel, B., Toward a Formal Model of Cognitive Synergy, Mar 2017, https://arxiv.org/abs/1703.04361 • Hauser, Hermann, Are Machines Better than Humans? Evening lecture on machine intelligence at SCI, London, 25 October 2017 https://www.youtube.com/watch?v=SVOMyEeXUow © Peter Morgan, May 2019
  • 117. Information Theory • Tishby, N. & R. Schwartz-Ziv, Opening the Black Box of Deep Neural Networks via Information, Apr 29, 2017, https://arxiv.org/abs/1703.00810 • Chaitin, G.J., From Philosophy to Program Size, Mar 2013, https://arxiv.org/abs/math/0303352 • Solomonoff, R.J., Machine Learning — Past and Future, Revision of lecture given at AI@50, The Dartmouth Artificial Intelligence Conference, July 13-15, 2006 • Publications of A. N. Kolmogorov, Annals of Probability, 17(3), July 1989 • Levin, L. A., Universal Sequential Search Problems, Problems of Information Transmission, 9(3), 1973 • Shannon, C.E., A Mathematical Theory of Communication, Bell System Technical Journal, 27 (3):379–423, July 1948 • AIT https://en.m.wikipedia.org/wiki/Algorithmic_information_theory © Peter Morgan, May 2019
  • 118. Classic Papers • Deutsch, David, The Constructor Theory of Life, Journal of the Royal Society Interface, 12(104), 2016 • Crick F., The recent excitement about neural networks, Nature 337:129–132, 1989 • Rumelhart DE, Hinton GE, Williams RJ, Learning representations by back-propagating errors, Nature 323:533–536, 1986 • Solomonoff, R.J., A Formal Theory of Inductive Inference, Part 1, Information and Control, 7(1), Mar, 1964, http://world.std.com/~rjs/1964pt1.ps • F. Rosenblatt, A probabilistic model for information storage and organization in the brain, Psych. Rev. 62, 386-407, 1958 • Turing, A.M., Computing Machinery and Intelligence, Mind 49:433-460, 1950 • Schrodinger, E., What is Life? Based on lectures delivered at Trinity College, Dublin, Feb 1943 http://www.whatislife.ie/downloads/What-is-Life.pdf • McCulloch, W.S. and W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 5(4):115–133, 1943 • Kolmogorov, A., On Analytical Methods in the Theory of Probability, Mathematische Annalen, 104(1), 1931 © Peter Morgan, May 2019
  • 119. Books • Sutton, R. S. & A.G. Barto, Reinforcement Learning, 2nd ed., MIT Press, 2018 • Goodfellow, I. et al, Deep Learning, Cambridge University Press, 2016 • Li, Ming and Paul Vitanyi, An Introduction to Kolmogorov Complexity and Its Applications. Springer-Verlag, N.Y., 2008 • Hutter M., Universal Artificial Intelligence, Springer–Verlag, 2004 • MacKay, David, Information theory, inference and learning algorithms, Cambridge University Press, 2003 • Wolfram, S., A New Kind of Science, Wolfram Media, 2002 • Hebb, D. O. The Organization of Behavior, A Neuropsychological Theory, John Wiley & Sons, 1949 © Peter Morgan, May 2019