SlideShare a Scribd company logo
An Inductive
Inference Machine
(1957)
R. J. Solomonoff
1926 - 2009
Aly O. Abdelkareem
University of Calgary
What is
Inductive
Inference ?
• Inductive inference is the process of reaching
a general conclusion from specific examples.
• The general conclusion should apply to unseen
examples.
Problem
• We will feed the machine these examples
• Here, we want the machine to decide upon
the most probable digit to fit into the empty
square
• Then, we present the machine with this problem
Solutions
N-grams and Prediction n-grams
N-tuples and Structures
N-gram Sets, Prediction n-gram
sets, N-tuple sets
N-Grams
Shannon has show how we may predict words or letters in
English by the use of “n-grams”
If we want to predict the next letter in ”Today we ar?”
• Using bi-gram
- Higher frequency of ”ra, rb, rc, re, rd … etc”
1. N-grams and Prediction n-grams
• N-grams: extend it to 2-grams
• Possibilities:
Prediction is consistent with the other examples
Consistency: of a Prediction n-gram to indicate that all of its predictions, as
applied to the examples given to the machine, have been correct
“=” and “0” are so close
What if we want the machine to find the
solution related to the “=“ ?
Is a spacer and it is not a proper part of the
prediction 3-gram
• N-tuples: is an ordered set of n object.
• Structure: set of instruction for taking the members of an N-tuple and
moving them in a certain way.
2- N-tuples and Structures
Applying N-tuple and Structure
• The structure
What if we have new
examples (unseen data) ?
It is unable to solve this problem, since it
cannot yet have learned the prediction 3-gram
3. Sets: N-gram Sets, Prediction n-gram sets,
N-tuple sets
• N-gram sets: unordered set of n-gram
• Prediction N-gram set: unordered set of prediction N grams
• N-tuple set: unordered set of N-tuple
Using sets we
can then
apply
Cartesian
product
Boolean
product
Boolean sum
Occurrence
operation
Occurrence Operation
Applying to
our problem
N-gram set
3-tuple set
Using this structure
Prediction on n-gram set will be
Limitations
High order sets:
Inability to deal with
members are themselves
sets
• Resolved by defining an N
tuple recursively.
Non- determistic:
Cannot work on problem
with several possible
answers ( language
translation, weather
prediction or information
retrieval.
Generalization:
Small error of input
disturb the machine
• Chomsky machine to find
grammatically correct
sentences
The concept
of Utility
• Utility values are assigned to each abstraction
used
• For example:
1. Prediction n grams: Consistent is 1 value –
high utility –
2. Structures or N-tuple: utility values
proportional to the frequency of create
consistent prediction
• Used to get a priori probability of consistency of
a new created prediction
Mode of
Operation of
Machine
Computer starts out with a small sets, along
with apriori utility assigned to all of them
Using set of transformation rules, the machine
creates a new set of abstractions from the old
set
Select combination with high apriori utilities
and apply empirical evaluation.
Keep the new good abstraction and then
Repeat
Goal:
• Find one that fit the problem
• if more than one fit, then find
the one with highest utility
• If the conflicting utility, then
the answer will not be reliable (
not many examples )
Important
problems that
must yet be
solved
SEARCHING FOR CONSISTENT
PREDICTION THAT FIT A
PARTICULAR QUESTION
SET OF RULES FOR THE
MANIPULATION OF THE SETS
NEED TO BE INVESTIGATED
ASSIGNING UTILITY MUST BE
WORKED OUT IN GREATER
DETAILS
THE OPERATING PROGRAM OF
THE STOCHASTIC MACHINE
HAS BEEN INVESTIGATED AT
GREATER LENGTH
METHODS OF GENERATING
NEW ABSTRACTION FROM
USEFUL OLD ONES MAY E
ADEQUATE.
REALIZING PHYSICALLY AN
INDUCTIVE INFERENCE
MACHINE (STORING INPUT
AND ACCESS SPEED )
3.75 MB
25 ms
Conclusion
• A program has been written for
a computer to learn to work
simple arithmetic problems
after being shown a set of
correctly worked examples
Summary
Accuracy of inference depends upon presented data
Machines takes examples that have been usefull in the past and
derive new reasonable examples
Machine to work on the problem of improving itself
given statistical training sequence
and probability distribution
The machine will be able to prove
theorems, play good chess, and answer
questions in English.
Example: Machine probably be able to recognize the difference
between “grammatically correct or incorrect”, providing a training
sequence of grammatically correct sentence
This paper
Implications
Solomonoff's theory of inductive inference
A mathematical formalization of Occam's razor and
Principle of Multiple Explanations.
Assumed the world is generated by an unknown
computer program.
Based on Algorithmic probability (Solomonoff
probability)
Prediction is done using a
completely Bayesian framework.
Background
Algorithms — We’re looking for an algorithm to
determine truth.
Induction — By “determine truth”, we mean
induction.
Occam’s Razor — How we judge between many
inductive hypotheses.
Probability — Probability is what we usually use
in induction.
The Problem of Priors — Probabilities change
with evidence, but where do they start?
The Solution
Binary Sequences — Everything can be encoded
as binary.
All Algorithms — Hypotheses are algorithms.
Turing machines describe these.
Solomonoff's Lightsaber — Putting it all together.
Formalized Science — From intuition to
precision.
Approximations — Ongoing work towards
practicality.
Unresolved Details — Problems, philosophical
and mathematical.
Solomonoff
induction
Algorithm
Make an observation.
Form a hypothesis that explains the observation.
Conduct an experiment that will test the hypothesis.
If the experimental results disconfirm the hypothesis, return to step #2
and form a hypothesis not yet used. If the experimental results confirm
the hypothesis, provisionally accept the hypothesis.
Now we’ve found the truth, as best as it can be found.
More Details
Bayes' rule: Guide
https://arbital.com/p/bayes_rule/?l=1zq
An Intuitive Explanation of Solomonoff
Induction
https://www.lesswrong.com/posts/Kyc5d
FDzBg4WccrbK/an-intuitive-explanation-
of-solomonoff-induction
How Bayes' theorem is consistent with
Solomonoff induction
https://www.lesswrong.com/posts/5pgsb
B5sqC2wLwr4d/how-bayes-theorem-is-
consistent-with-solomonoff-induction
Thank you

More Related Content

Similar to An Inductive inference Machine

Neural network for machine learning
Neural network for machine learningNeural network for machine learning
Neural network for machine learning
Ujjawal
 
NLP_KASHK:Evaluating Language Model
NLP_KASHK:Evaluating Language ModelNLP_KASHK:Evaluating Language Model
NLP_KASHK:Evaluating Language Model
Hemantha Kulathilake
 
Py data19 final
Py data19   finalPy data19   final
Py data19 final
Maria Navarro Jiménez
 
Language models
Language modelsLanguage models
Language models
Maryam Khordad
 
NLP_KASHK:N-Grams
NLP_KASHK:N-GramsNLP_KASHK:N-Grams
NLP_KASHK:N-Grams
Hemantha Kulathilake
 
ML_Unit_2_Part_A
ML_Unit_2_Part_AML_Unit_2_Part_A
ML_Unit_2_Part_A
Srimatre K
 
Lecture 6
Lecture 6Lecture 6
Lecture 6
hunglq
 
MM - KBAC: Using mixed models to adjust for population structure in a rare-va...
MM - KBAC: Using mixed models to adjust for population structure in a rare-va...MM - KBAC: Using mixed models to adjust for population structure in a rare-va...
MM - KBAC: Using mixed models to adjust for population structure in a rare-va...
Golden Helix Inc
 
lec09_ransac.pptx
lec09_ransac.pptxlec09_ransac.pptx
lec09_ransac.pptx
AneesAbbasi14
 
Machine learning (5)
Machine learning (5)Machine learning (5)
Machine learning (5)
NYversity
 
Artificial Neural Networks 1
Artificial Neural Networks 1Artificial Neural Networks 1
Artificial Neural Networks 1
swapnac12
 
Supervised and unsupervised learning
Supervised and unsupervised learningSupervised and unsupervised learning
Supervised and unsupervised learning
AmAn Singh
 
DAA UNIT 3
DAA UNIT 3DAA UNIT 3
DAA UNIT 3
SURBHI SAROHA
 
Deep learning MindMap
Deep learning MindMapDeep learning MindMap
Deep learning MindMap
Ashish Patel
 
AI Algorithms
AI AlgorithmsAI Algorithms
AI Algorithms
Dr. C.V. Suresh Babu
 
Computer Vision - RANSAC
Computer Vision - RANSACComputer Vision - RANSAC
Computer Vision - RANSAC
Wael Badawy
 
Essentials of machine learning algorithms
Essentials of machine learning algorithmsEssentials of machine learning algorithms
Essentials of machine learning algorithms
Arunangsu Sahu
 
Or ppt,new
Or ppt,newOr ppt,new
Or ppt,new
Roy Thomas
 
Into to prob_prog_hari
Into to prob_prog_hariInto to prob_prog_hari
Into to prob_prog_hari
Hariharan Chandrasekaran
 
Ml ppt at
Ml ppt atMl ppt at
Ml ppt at
pradeep kumar
 

Similar to An Inductive inference Machine (20)

Neural network for machine learning
Neural network for machine learningNeural network for machine learning
Neural network for machine learning
 
NLP_KASHK:Evaluating Language Model
NLP_KASHK:Evaluating Language ModelNLP_KASHK:Evaluating Language Model
NLP_KASHK:Evaluating Language Model
 
Py data19 final
Py data19   finalPy data19   final
Py data19 final
 
Language models
Language modelsLanguage models
Language models
 
NLP_KASHK:N-Grams
NLP_KASHK:N-GramsNLP_KASHK:N-Grams
NLP_KASHK:N-Grams
 
ML_Unit_2_Part_A
ML_Unit_2_Part_AML_Unit_2_Part_A
ML_Unit_2_Part_A
 
Lecture 6
Lecture 6Lecture 6
Lecture 6
 
MM - KBAC: Using mixed models to adjust for population structure in a rare-va...
MM - KBAC: Using mixed models to adjust for population structure in a rare-va...MM - KBAC: Using mixed models to adjust for population structure in a rare-va...
MM - KBAC: Using mixed models to adjust for population structure in a rare-va...
 
lec09_ransac.pptx
lec09_ransac.pptxlec09_ransac.pptx
lec09_ransac.pptx
 
Machine learning (5)
Machine learning (5)Machine learning (5)
Machine learning (5)
 
Artificial Neural Networks 1
Artificial Neural Networks 1Artificial Neural Networks 1
Artificial Neural Networks 1
 
Supervised and unsupervised learning
Supervised and unsupervised learningSupervised and unsupervised learning
Supervised and unsupervised learning
 
DAA UNIT 3
DAA UNIT 3DAA UNIT 3
DAA UNIT 3
 
Deep learning MindMap
Deep learning MindMapDeep learning MindMap
Deep learning MindMap
 
AI Algorithms
AI AlgorithmsAI Algorithms
AI Algorithms
 
Computer Vision - RANSAC
Computer Vision - RANSACComputer Vision - RANSAC
Computer Vision - RANSAC
 
Essentials of machine learning algorithms
Essentials of machine learning algorithmsEssentials of machine learning algorithms
Essentials of machine learning algorithms
 
Or ppt,new
Or ppt,newOr ppt,new
Or ppt,new
 
Into to prob_prog_hari
Into to prob_prog_hariInto to prob_prog_hari
Into to prob_prog_hari
 
Ml ppt at
Ml ppt atMl ppt at
Ml ppt at
 

More from Aly Abdelkareem

Digital Image Processing - Frequency Filters
Digital Image Processing - Frequency FiltersDigital Image Processing - Frequency Filters
Digital Image Processing - Frequency Filters
Aly Abdelkareem
 
Deep learning: Overfitting , underfitting, and regularization
Deep learning: Overfitting , underfitting, and regularizationDeep learning: Overfitting , underfitting, and regularization
Deep learning: Overfitting , underfitting, and regularization
Aly Abdelkareem
 
Practical Digital Image Processing 5
Practical Digital Image Processing 5Practical Digital Image Processing 5
Practical Digital Image Processing 5
Aly Abdelkareem
 
Practical Digital Image Processing 4
Practical Digital Image Processing 4Practical Digital Image Processing 4
Practical Digital Image Processing 4
Aly Abdelkareem
 
Practical Digital Image Processing 3
 Practical Digital Image Processing 3 Practical Digital Image Processing 3
Practical Digital Image Processing 3
Aly Abdelkareem
 
Pattern recognition 4 - MLE
Pattern recognition 4 - MLEPattern recognition 4 - MLE
Pattern recognition 4 - MLE
Aly Abdelkareem
 
Practical Digital Image Processing 2
Practical Digital Image Processing 2Practical Digital Image Processing 2
Practical Digital Image Processing 2
Aly Abdelkareem
 
Practical Digital Image Processing 1
Practical Digital Image Processing 1Practical Digital Image Processing 1
Practical Digital Image Processing 1
Aly Abdelkareem
 
Machine Learning for Everyone
Machine Learning for EveryoneMachine Learning for Everyone
Machine Learning for Everyone
Aly Abdelkareem
 
How to use deep learning on biological data
How to use deep learning on biological dataHow to use deep learning on biological data
How to use deep learning on biological data
Aly Abdelkareem
 
Deep Learning using Keras
Deep Learning using KerasDeep Learning using Keras
Deep Learning using Keras
Aly Abdelkareem
 
Object extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningObject extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learning
Aly Abdelkareem
 
Pattern recognition Tutorial 2
Pattern recognition Tutorial 2Pattern recognition Tutorial 2
Pattern recognition Tutorial 2
Aly Abdelkareem
 
Android Udacity Study group 1
Android Udacity Study group 1Android Udacity Study group 1
Android Udacity Study group 1
Aly Abdelkareem
 
Java for android developers
Java for android developersJava for android developers
Java for android developers
Aly Abdelkareem
 
Introduction to Android Development
Introduction to Android DevelopmentIntroduction to Android Development
Introduction to Android Development
Aly Abdelkareem
 

More from Aly Abdelkareem (16)

Digital Image Processing - Frequency Filters
Digital Image Processing - Frequency FiltersDigital Image Processing - Frequency Filters
Digital Image Processing - Frequency Filters
 
Deep learning: Overfitting , underfitting, and regularization
Deep learning: Overfitting , underfitting, and regularizationDeep learning: Overfitting , underfitting, and regularization
Deep learning: Overfitting , underfitting, and regularization
 
Practical Digital Image Processing 5
Practical Digital Image Processing 5Practical Digital Image Processing 5
Practical Digital Image Processing 5
 
Practical Digital Image Processing 4
Practical Digital Image Processing 4Practical Digital Image Processing 4
Practical Digital Image Processing 4
 
Practical Digital Image Processing 3
 Practical Digital Image Processing 3 Practical Digital Image Processing 3
Practical Digital Image Processing 3
 
Pattern recognition 4 - MLE
Pattern recognition 4 - MLEPattern recognition 4 - MLE
Pattern recognition 4 - MLE
 
Practical Digital Image Processing 2
Practical Digital Image Processing 2Practical Digital Image Processing 2
Practical Digital Image Processing 2
 
Practical Digital Image Processing 1
Practical Digital Image Processing 1Practical Digital Image Processing 1
Practical Digital Image Processing 1
 
Machine Learning for Everyone
Machine Learning for EveryoneMachine Learning for Everyone
Machine Learning for Everyone
 
How to use deep learning on biological data
How to use deep learning on biological dataHow to use deep learning on biological data
How to use deep learning on biological data
 
Deep Learning using Keras
Deep Learning using KerasDeep Learning using Keras
Deep Learning using Keras
 
Object extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningObject extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learning
 
Pattern recognition Tutorial 2
Pattern recognition Tutorial 2Pattern recognition Tutorial 2
Pattern recognition Tutorial 2
 
Android Udacity Study group 1
Android Udacity Study group 1Android Udacity Study group 1
Android Udacity Study group 1
 
Java for android developers
Java for android developersJava for android developers
Java for android developers
 
Introduction to Android Development
Introduction to Android DevelopmentIntroduction to Android Development
Introduction to Android Development
 

Recently uploaded

ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
VANDANAMOHANGOUDA
 
一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理
一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理
一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理
nonods
 
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
Paris Salesforce Developer Group
 
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
upoux
 
Flow Through Pipe: the analysis of fluid flow within pipes
Flow Through Pipe:  the analysis of fluid flow within pipesFlow Through Pipe:  the analysis of fluid flow within pipes
Flow Through Pipe: the analysis of fluid flow within pipes
Indrajeet sahu
 
Accident detection system project report.pdf
Accident detection system project report.pdfAccident detection system project report.pdf
Accident detection system project report.pdf
Kamal Acharya
 
Determination of Equivalent Circuit parameters and performance characteristic...
Determination of Equivalent Circuit parameters and performance characteristic...Determination of Equivalent Circuit parameters and performance characteristic...
Determination of Equivalent Circuit parameters and performance characteristic...
pvpriya2
 
Northrop Grumman - Aerospace Structures Overvi.pdf
Northrop Grumman - Aerospace Structures Overvi.pdfNorthrop Grumman - Aerospace Structures Overvi.pdf
Northrop Grumman - Aerospace Structures Overvi.pdf
takipo7507
 
UNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICS
UNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICSUNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICS
UNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICS
vmspraneeth
 
OOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming languageOOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming language
PreethaV16
 
An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...
An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...
An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...
DharmaBanothu
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
uqyfuc
 
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
OKORIE1
 
openshift technical overview - Flow of openshift containerisatoin
openshift technical overview - Flow of openshift containerisatoinopenshift technical overview - Flow of openshift containerisatoin
openshift technical overview - Flow of openshift containerisatoin
snaprevwdev
 
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
PriyankaKilaniya
 
Butterfly Valves Manufacturer (LBF Series).pdf
Butterfly Valves Manufacturer (LBF Series).pdfButterfly Valves Manufacturer (LBF Series).pdf
Butterfly Valves Manufacturer (LBF Series).pdf
Lubi Valves
 
paper relate Chozhavendhan et al. 2020.pdf
paper relate Chozhavendhan et al. 2020.pdfpaper relate Chozhavendhan et al. 2020.pdf
paper relate Chozhavendhan et al. 2020.pdf
ShurooqTaib
 
一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理
一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理
一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理
sydezfe
 
Introduction to Computer Networks & OSI MODEL.ppt
Introduction to Computer Networks & OSI MODEL.pptIntroduction to Computer Networks & OSI MODEL.ppt
Introduction to Computer Networks & OSI MODEL.ppt
Dwarkadas J Sanghvi College of Engineering
 
Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...
Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...
Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...
IJCNCJournal
 

Recently uploaded (20)

ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
 
一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理
一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理
一比一原版(psu学位证书)美国匹兹堡州立大学毕业证如何办理
 
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
 
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
 
Flow Through Pipe: the analysis of fluid flow within pipes
Flow Through Pipe:  the analysis of fluid flow within pipesFlow Through Pipe:  the analysis of fluid flow within pipes
Flow Through Pipe: the analysis of fluid flow within pipes
 
Accident detection system project report.pdf
Accident detection system project report.pdfAccident detection system project report.pdf
Accident detection system project report.pdf
 
Determination of Equivalent Circuit parameters and performance characteristic...
Determination of Equivalent Circuit parameters and performance characteristic...Determination of Equivalent Circuit parameters and performance characteristic...
Determination of Equivalent Circuit parameters and performance characteristic...
 
Northrop Grumman - Aerospace Structures Overvi.pdf
Northrop Grumman - Aerospace Structures Overvi.pdfNorthrop Grumman - Aerospace Structures Overvi.pdf
Northrop Grumman - Aerospace Structures Overvi.pdf
 
UNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICS
UNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICSUNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICS
UNIT 4 LINEAR INTEGRATED CIRCUITS-DIGITAL ICS
 
OOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming languageOOPS_Lab_Manual - programs using C++ programming language
OOPS_Lab_Manual - programs using C++ programming language
 
An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...
An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...
An In-Depth Exploration of Natural Language Processing: Evolution, Applicatio...
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
 
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
 
openshift technical overview - Flow of openshift containerisatoin
openshift technical overview - Flow of openshift containerisatoinopenshift technical overview - Flow of openshift containerisatoin
openshift technical overview - Flow of openshift containerisatoin
 
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
Prediction of Electrical Energy Efficiency Using Information on Consumer's Ac...
 
Butterfly Valves Manufacturer (LBF Series).pdf
Butterfly Valves Manufacturer (LBF Series).pdfButterfly Valves Manufacturer (LBF Series).pdf
Butterfly Valves Manufacturer (LBF Series).pdf
 
paper relate Chozhavendhan et al. 2020.pdf
paper relate Chozhavendhan et al. 2020.pdfpaper relate Chozhavendhan et al. 2020.pdf
paper relate Chozhavendhan et al. 2020.pdf
 
一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理
一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理
一比一原版(uoft毕业证书)加拿大多伦多大学毕业证如何办理
 
Introduction to Computer Networks & OSI MODEL.ppt
Introduction to Computer Networks & OSI MODEL.pptIntroduction to Computer Networks & OSI MODEL.ppt
Introduction to Computer Networks & OSI MODEL.ppt
 
Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...
Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...
Particle Swarm Optimization–Long Short-Term Memory based Channel Estimation w...
 

An Inductive inference Machine

  • 1. An Inductive Inference Machine (1957) R. J. Solomonoff 1926 - 2009 Aly O. Abdelkareem University of Calgary
  • 2. What is Inductive Inference ? • Inductive inference is the process of reaching a general conclusion from specific examples. • The general conclusion should apply to unseen examples.
  • 3. Problem • We will feed the machine these examples • Here, we want the machine to decide upon the most probable digit to fit into the empty square • Then, we present the machine with this problem
  • 4. Solutions N-grams and Prediction n-grams N-tuples and Structures N-gram Sets, Prediction n-gram sets, N-tuple sets
  • 5. N-Grams Shannon has show how we may predict words or letters in English by the use of “n-grams” If we want to predict the next letter in ”Today we ar?” • Using bi-gram - Higher frequency of ”ra, rb, rc, re, rd … etc”
  • 6. 1. N-grams and Prediction n-grams • N-grams: extend it to 2-grams • Possibilities: Prediction is consistent with the other examples Consistency: of a Prediction n-gram to indicate that all of its predictions, as applied to the examples given to the machine, have been correct
  • 7. “=” and “0” are so close What if we want the machine to find the solution related to the “=“ ? Is a spacer and it is not a proper part of the prediction 3-gram
  • 8. • N-tuples: is an ordered set of n object. • Structure: set of instruction for taking the members of an N-tuple and moving them in a certain way. 2- N-tuples and Structures
  • 9. Applying N-tuple and Structure • The structure
  • 10. What if we have new examples (unseen data) ? It is unable to solve this problem, since it cannot yet have learned the prediction 3-gram
  • 11. 3. Sets: N-gram Sets, Prediction n-gram sets, N-tuple sets • N-gram sets: unordered set of n-gram • Prediction N-gram set: unordered set of prediction N grams • N-tuple set: unordered set of N-tuple
  • 12. Using sets we can then apply Cartesian product Boolean product Boolean sum Occurrence operation
  • 14. Applying to our problem N-gram set 3-tuple set Using this structure Prediction on n-gram set will be
  • 15. Limitations High order sets: Inability to deal with members are themselves sets • Resolved by defining an N tuple recursively. Non- determistic: Cannot work on problem with several possible answers ( language translation, weather prediction or information retrieval. Generalization: Small error of input disturb the machine • Chomsky machine to find grammatically correct sentences
  • 16. The concept of Utility • Utility values are assigned to each abstraction used • For example: 1. Prediction n grams: Consistent is 1 value – high utility – 2. Structures or N-tuple: utility values proportional to the frequency of create consistent prediction • Used to get a priori probability of consistency of a new created prediction
  • 17. Mode of Operation of Machine Computer starts out with a small sets, along with apriori utility assigned to all of them Using set of transformation rules, the machine creates a new set of abstractions from the old set Select combination with high apriori utilities and apply empirical evaluation. Keep the new good abstraction and then Repeat Goal: • Find one that fit the problem • if more than one fit, then find the one with highest utility • If the conflicting utility, then the answer will not be reliable ( not many examples )
  • 18. Important problems that must yet be solved SEARCHING FOR CONSISTENT PREDICTION THAT FIT A PARTICULAR QUESTION SET OF RULES FOR THE MANIPULATION OF THE SETS NEED TO BE INVESTIGATED ASSIGNING UTILITY MUST BE WORKED OUT IN GREATER DETAILS THE OPERATING PROGRAM OF THE STOCHASTIC MACHINE HAS BEEN INVESTIGATED AT GREATER LENGTH METHODS OF GENERATING NEW ABSTRACTION FROM USEFUL OLD ONES MAY E ADEQUATE. REALIZING PHYSICALLY AN INDUCTIVE INFERENCE MACHINE (STORING INPUT AND ACCESS SPEED ) 3.75 MB 25 ms
  • 19. Conclusion • A program has been written for a computer to learn to work simple arithmetic problems after being shown a set of correctly worked examples
  • 20. Summary Accuracy of inference depends upon presented data Machines takes examples that have been usefull in the past and derive new reasonable examples Machine to work on the problem of improving itself given statistical training sequence and probability distribution The machine will be able to prove theorems, play good chess, and answer questions in English. Example: Machine probably be able to recognize the difference between “grammatically correct or incorrect”, providing a training sequence of grammatically correct sentence
  • 21. This paper Implications Solomonoff's theory of inductive inference A mathematical formalization of Occam's razor and Principle of Multiple Explanations. Assumed the world is generated by an unknown computer program. Based on Algorithmic probability (Solomonoff probability) Prediction is done using a completely Bayesian framework.
  • 22. Background Algorithms — We’re looking for an algorithm to determine truth. Induction — By “determine truth”, we mean induction. Occam’s Razor — How we judge between many inductive hypotheses. Probability — Probability is what we usually use in induction. The Problem of Priors — Probabilities change with evidence, but where do they start? The Solution Binary Sequences — Everything can be encoded as binary. All Algorithms — Hypotheses are algorithms. Turing machines describe these. Solomonoff's Lightsaber — Putting it all together. Formalized Science — From intuition to precision. Approximations — Ongoing work towards practicality. Unresolved Details — Problems, philosophical and mathematical.
  • 23.
  • 24. Solomonoff induction Algorithm Make an observation. Form a hypothesis that explains the observation. Conduct an experiment that will test the hypothesis. If the experimental results disconfirm the hypothesis, return to step #2 and form a hypothesis not yet used. If the experimental results confirm the hypothesis, provisionally accept the hypothesis. Now we’ve found the truth, as best as it can be found.
  • 25. More Details Bayes' rule: Guide https://arbital.com/p/bayes_rule/?l=1zq An Intuitive Explanation of Solomonoff Induction https://www.lesswrong.com/posts/Kyc5d FDzBg4WccrbK/an-intuitive-explanation- of-solomonoff-induction How Bayes' theorem is consistent with Solomonoff induction https://www.lesswrong.com/posts/5pgsb B5sqC2wLwr4d/how-bayes-theorem-is- consistent-with-solomonoff-induction