SlideShare a Scribd company logo
1 of 54
Download to read offline
Artificial Intelligence
Foundational ideas, applications & issues
Dr. Jayanti Prasad
DISYS India Pvt. Ltd. Chennai
June 07, 2023, Anna University Chennai
Agenda
● Natural language Processing
○ Text Vectorization
○ Seq2Seq Modeling
○ Attention
○ Transformers
● Physics & AI
● Responsible AI
○ Explainable AI
○ Safe AI
○ Fair AI
● Conclusions
● Introduction
○ Fourth paradigm of science
○ Fourth Industrial revolution
○ Why AI today
○ What is AI
○ What is data science ?
● Learning & Intelligence
○ Bayesian Learning
○ Type of AI
○ Deep Learning 2
3
1. Empirical observations
2. Theory
3. Computation
4. Data driven discovery
“No longer restricted to data analysis, machine learning is now increasingly being used in
theory, experiment and simulation — a sign that data-intensive science is starting to
encompass all traditional aspects of research.”
Fourth paradigm of science
Fourth Industrial revolution
4
WHY AI Today ?
5
Moore’s Law Data explosion
Algorithms timeline
6
• Seq2Aeq
• Attention
• Transformers
2015-
ImageNet
o The ImageNet project is a large visual database designed for
use in visual object recognition software research.
o ImageNet database has more than 14 million images in
20,000 categories (labelled).
o In 2012 competition one neural network named AlexNet
achieved 84 % accuracy, quite close to humans.
7
8
AI revolution in Language
9
Citations
Title
Authors
Year
84,605
Long Short-Term Memory
Sepp Hochreiter and
Jürgen Schmidhuber
1997
22,422
Sequence to Sequence
Learning with Neural Networks
Ilya Sutskever, Oriol
Vinyals, Quoc V. Le
2014
76,820
Attention Is All You Need !
Ashish Vaswani, Noam
Shazeer, Niki Parmar, Jakob
Uszkoreit, Llion Jones, Aidan
N. Gomez, Lukasz Kaiser, Illia
Polosukhin
2017
67,875
BERT: Pre-training of Deep
Bidirectional Transformers for
Language Understanding
Jacob Devlin, Ming-Wei
Chang, Kenton Lee, Kristina
Toutanova
2018
5,592
Improving Language
Understanding by Generative
Pre-Training
Alec Radford, Karthik
Narasimhan, Tim
Salimans, Ilya Sutskever
2019
What exactly is AI ?
Type of AI
11
Thinking
Humanly
Thinking
Rationally
Acting
Humanly
Acting
rationally
1. Natural Language Processing (NLP)
2. Knowledge Representation
3. Automated Reasoning
4. Machine Learning – Learning from experience (data)
5. Computer Vision
6. Robotics
Turing Test
Machine Learning
● A computer program is said to learn from experience ‘E’
with respect to some class of tasks ‘T’ and performance
measure ‘P’, if its performance at tasks in ‘T’, as measured
by P, improves with experience ‘E’.”
- Tom Mitchell
 Experience (E) - Data
 Task (T) – Classification / Regression
 Performance (P) – Loss, accuracy
-
12
Machine Learning
13
Machine
Learning
Supervised
Unsupervised
Reinforcement
Hybrid
Data Science
Data science combines math and statistics, specialized programming, advanced
analytics, artificial intelligence (AI), and machine learning with specific subject
matter expertise to uncover actionable insights hidden in an organization’s
data. These insights can be used to guide decision making and strategic
planning
14
 Mathematics (Linear Algebra & Calculus)
 Probability & Statistics
 Specialized programming
 Artificial Intelligence & Machine Learning
 Subject matter expertise
Data science lifecycle
15
Business Understanding / use case discovery
Data collection
Data pre-processing (cleaning, featurization etc.,)
Data modeling
Model evaluation
Model deployment
Bayesian Learning
Bayesian probability
● Conditional Probability
=
● Bayes’ Theorem
● Posterior (model) = Likelihood (data, model) * Prior (model)
17
Bayesian Model Fitting
18
A = Model
B = Data
Example
● Model : Fitting a line
● Data :
● Likelihood :
∗
=
● Posterior :
19
Discriminative vs Generative Models
● Discriminative models capture conditional
probability P(y | X)
● Generative models capture joint probability P(X, y)
or just P(X) if there are no labels.
● A generative model includes the distribution of the data itself and tells
you how likely a given example is. For example, models that predict
the next word in a sequence are typically generative models (usually
much simpler than GANs) because they can assign a probability to a
sequence of words.
20
Supervised Machine Leraning
21
Supervised Machine Learning
● Data : where and either (regression) or
where
● Model
, in general it is a non-linear function.
● Loss function : Quantifies the mismatch between the actual
output and predicted output ,
● Training : Minimize the loss against the weights / parameters of
the model.
22
Common Loss functions
● Mean Squared Error (regression)
= , (for linear cases)
● Cross Entropy (classification)
+
● Activation (non-linear) function:
Sigmoid : p(X) = ( ∗ )
23
24
Artificial Neuron /Perceptron
25
Optimization
● Supervised machine learning is all about finding the model
parameters or ‘weights’ which can represent the non-linear
mapping between the input (features) and the output.
● Finding a set of parameters which minimizes the ‘mismatch’
or loss between the actual output and predicted output is
called ‘optimization’.
● There are many optimization schemes and one of the most
common is ‘gradient descent’.
26
Gradient descent
● It is an optimization scheme to find the model parameters
iteratively by minimizing the loss function
27
Deep Learning
29
Deep Learning
30
Deep Learning
31
Two key properties of
artificial neural networks
33
Automatic feature learning
34
Text Modeling
Data Classification
36
Data
Numerical
(value)
Continuous
Discrete
Ordinal
Nominal
Symbolic
(meaning)
Challenges in modeling text
● Computers are good in numerical computation / number
crunching
● Numerical operations (+,-,x,/) are not possible on text.
● There is way to get relations like the following one.
King – Man + Women = Queen !
37
Vectorization / Latent space
● Let us consider the text :
Data = “quick brown fox jumped over the lazy dog “
● Assign unique id to each word/symbol and build a
vocabulary.
● Now represent each word with a vector (one hot encoding) of
the size of the vocabulary.
● Unfortunately, the dimensionality of the vector is very high
and all the entries except one are zeroes.
38
Word Embedding
● Let us consider a one hot encoded vector X N is
the size of the vocabulary.
● We can find a matrix such that
Here
● In common English used we have around 40,000 words
(N=40,000) and we generally have M = 300.
● There are many pre-trained models to get vectorizd form of
words, such as Glove and Word2Vec
39
Word Vectors
40
41
42
Three revolutionary
neural network
architectures
(1) Seq2Seq Model
44
“The encoder processes each item in the input sequence, it compiles the information it captures
into a vector (called the context). After processing the entire input sequence, the encoder
sends the context over to the decoder, which begins producing the output sequence item by item.”
RNN (LSTM)
Encoder-Decoder
(2) Attention
45
(3) Transformer
46
GPT4
47
Physics & AI
49
50
Responsible AI
● Explainable AI
● Safe AI
● Fair AI / Unbiased
51
Questions ?
Thank you !
References
1. A high-bias, low-variance introduction to Machine Learning for physicists
2. Statistical Mechanics of deep learning
3. Discovering Physical Concepts with Neural Networks
4. Physics-informed machine learning
5. On scientific understanding with artificial intelligence
6. AI Feynman: A physics-inspired method for symbolic regression
7. Defining physicists’ relationship with AI
8. Machine intelligence – Nature insight
9. Rise of the Machines – Science special issue
10.https://prasad-jayanti.medium.com/
eargatisticanicee 54

More Related Content

Similar to Artificial Intelligence - Anna Uni -v1.pdf

Machine learning for sensor Data Analytics
Machine learning for sensor Data AnalyticsMachine learning for sensor Data Analytics
Machine learning for sensor Data AnalyticsMATLABISRAEL
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxVenkateswaraBabuRavi
 
.NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво...
.NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво....NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво...
.NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво...NETFest
 
Presentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data MiningPresentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data Miningbutest
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
A step towards machine learning at accionlabs
A step towards machine learning at accionlabsA step towards machine learning at accionlabs
A step towards machine learning at accionlabsChetan Khatri
 
Introduction to soft computing V 1.0
Introduction to soft computing  V 1.0Introduction to soft computing  V 1.0
Introduction to soft computing V 1.0Dr. C.V. Suresh Babu
 
A quick peek into the word of AI
A quick peek into the word of AIA quick peek into the word of AI
A quick peek into the word of AISubhendu Dey
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Codemotion
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisionsDeepu S Nath
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisionsDeepu S Nath
 
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Mathieu DESPRIEE
 
How to use Artificial Intelligence with Python? Edureka
How to use Artificial Intelligence with Python? EdurekaHow to use Artificial Intelligence with Python? Edureka
How to use Artificial Intelligence with Python? EdurekaEdureka!
 
Machine learning 101
Machine learning 101Machine learning 101
Machine learning 101AmmarChalifah
 
Regression with Microsoft Azure & Ms Excel
Regression with Microsoft Azure & Ms ExcelRegression with Microsoft Azure & Ms Excel
Regression with Microsoft Azure & Ms ExcelDr. Abdul Ahad Abro
 
Big Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloBig Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloOCTO Technology
 
Fundementals of Machine Learning and Deep Learning
Fundementals of Machine Learning and Deep Learning Fundementals of Machine Learning and Deep Learning
Fundementals of Machine Learning and Deep Learning ParrotAI
 

Similar to Artificial Intelligence - Anna Uni -v1.pdf (20)

AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Machine learning for sensor Data Analytics
Machine learning for sensor Data AnalyticsMachine learning for sensor Data Analytics
Machine learning for sensor Data Analytics
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptx
 
.NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво...
.NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво....NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво...
.NET Fest 2017. Игорь Кочетов. Классификация результатов тестирования произво...
 
Presentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data MiningPresentation on Machine Learning and Data Mining
Presentation on Machine Learning and Data Mining
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
A step towards machine learning at accionlabs
A step towards machine learning at accionlabsA step towards machine learning at accionlabs
A step towards machine learning at accionlabs
 
Introduction to soft computing V 1.0
Introduction to soft computing  V 1.0Introduction to soft computing  V 1.0
Introduction to soft computing V 1.0
 
A quick peek into the word of AI
A quick peek into the word of AIA quick peek into the word of AI
A quick peek into the word of AI
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisions
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisions
 
AI Presentation 1
AI Presentation 1AI Presentation 1
AI Presentation 1
 
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
 
How to use Artificial Intelligence with Python? Edureka
How to use Artificial Intelligence with Python? EdurekaHow to use Artificial Intelligence with Python? Edureka
How to use Artificial Intelligence with Python? Edureka
 
Machine learning 101
Machine learning 101Machine learning 101
Machine learning 101
 
Regression with Microsoft Azure & Ms Excel
Regression with Microsoft Azure & Ms ExcelRegression with Microsoft Azure & Ms Excel
Regression with Microsoft Azure & Ms Excel
 
Lec1 intoduction.pptx
Lec1 intoduction.pptxLec1 intoduction.pptx
Lec1 intoduction.pptx
 
Big Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloBig Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao Paulo
 
Fundementals of Machine Learning and Deep Learning
Fundementals of Machine Learning and Deep Learning Fundementals of Machine Learning and Deep Learning
Fundementals of Machine Learning and Deep Learning
 

More from Jayanti Prasad Ph.D. (14)

parallel-computation.pdf
parallel-computation.pdfparallel-computation.pdf
parallel-computation.pdf
 
thesis_seminar.pdf
thesis_seminar.pdfthesis_seminar.pdf
thesis_seminar.pdf
 
pso2015.pdf
pso2015.pdfpso2015.pdf
pso2015.pdf
 
nbody_iitk.pdf
nbody_iitk.pdfnbody_iitk.pdf
nbody_iitk.pdf
 
likelihood_p2.pdf
likelihood_p2.pdflikelihood_p2.pdf
likelihood_p2.pdf
 
likelihood_p1.pdf
likelihood_p1.pdflikelihood_p1.pdf
likelihood_p1.pdf
 
doing_parallel.pdf
doing_parallel.pdfdoing_parallel.pdf
doing_parallel.pdf
 
Scikit-learn1
Scikit-learn1Scikit-learn1
Scikit-learn1
 
CMB Likelihood Part 2
CMB Likelihood Part 2CMB Likelihood Part 2
CMB Likelihood Part 2
 
CMB Likelihood Part 1
CMB Likelihood Part 1CMB Likelihood Part 1
CMB Likelihood Part 1
 
Cmb part3
Cmb part3Cmb part3
Cmb part3
 
Cmb part2
Cmb part2Cmb part2
Cmb part2
 
Cmb part1
Cmb part1Cmb part1
Cmb part1
 
Parallel computation
Parallel computationParallel computation
Parallel computation
 

Recently uploaded

Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
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
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 

Recently uploaded (20)

Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic 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...
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 

Artificial Intelligence - Anna Uni -v1.pdf

  • 1. Artificial Intelligence Foundational ideas, applications & issues Dr. Jayanti Prasad DISYS India Pvt. Ltd. Chennai June 07, 2023, Anna University Chennai
  • 2. Agenda ● Natural language Processing ○ Text Vectorization ○ Seq2Seq Modeling ○ Attention ○ Transformers ● Physics & AI ● Responsible AI ○ Explainable AI ○ Safe AI ○ Fair AI ● Conclusions ● Introduction ○ Fourth paradigm of science ○ Fourth Industrial revolution ○ Why AI today ○ What is AI ○ What is data science ? ● Learning & Intelligence ○ Bayesian Learning ○ Type of AI ○ Deep Learning 2
  • 3. 3 1. Empirical observations 2. Theory 3. Computation 4. Data driven discovery “No longer restricted to data analysis, machine learning is now increasingly being used in theory, experiment and simulation — a sign that data-intensive science is starting to encompass all traditional aspects of research.” Fourth paradigm of science
  • 5. WHY AI Today ? 5 Moore’s Law Data explosion
  • 6. Algorithms timeline 6 • Seq2Aeq • Attention • Transformers 2015-
  • 7. ImageNet o The ImageNet project is a large visual database designed for use in visual object recognition software research. o ImageNet database has more than 14 million images in 20,000 categories (labelled). o In 2012 competition one neural network named AlexNet achieved 84 % accuracy, quite close to humans. 7
  • 8. 8
  • 9. AI revolution in Language 9 Citations Title Authors Year 84,605 Long Short-Term Memory Sepp Hochreiter and Jürgen Schmidhuber 1997 22,422 Sequence to Sequence Learning with Neural Networks Ilya Sutskever, Oriol Vinyals, Quoc V. Le 2014 76,820 Attention Is All You Need ! Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin 2017 67,875 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova 2018 5,592 Improving Language Understanding by Generative Pre-Training Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever 2019
  • 11. Type of AI 11 Thinking Humanly Thinking Rationally Acting Humanly Acting rationally 1. Natural Language Processing (NLP) 2. Knowledge Representation 3. Automated Reasoning 4. Machine Learning – Learning from experience (data) 5. Computer Vision 6. Robotics Turing Test
  • 12. Machine Learning ● A computer program is said to learn from experience ‘E’ with respect to some class of tasks ‘T’ and performance measure ‘P’, if its performance at tasks in ‘T’, as measured by P, improves with experience ‘E’.” - Tom Mitchell  Experience (E) - Data  Task (T) – Classification / Regression  Performance (P) – Loss, accuracy - 12
  • 14. Data Science Data science combines math and statistics, specialized programming, advanced analytics, artificial intelligence (AI), and machine learning with specific subject matter expertise to uncover actionable insights hidden in an organization’s data. These insights can be used to guide decision making and strategic planning 14  Mathematics (Linear Algebra & Calculus)  Probability & Statistics  Specialized programming  Artificial Intelligence & Machine Learning  Subject matter expertise
  • 15. Data science lifecycle 15 Business Understanding / use case discovery Data collection Data pre-processing (cleaning, featurization etc.,) Data modeling Model evaluation Model deployment
  • 17. Bayesian probability ● Conditional Probability = ● Bayes’ Theorem ● Posterior (model) = Likelihood (data, model) * Prior (model) 17
  • 18. Bayesian Model Fitting 18 A = Model B = Data
  • 19. Example ● Model : Fitting a line ● Data : ● Likelihood : ∗ = ● Posterior : 19
  • 20. Discriminative vs Generative Models ● Discriminative models capture conditional probability P(y | X) ● Generative models capture joint probability P(X, y) or just P(X) if there are no labels. ● A generative model includes the distribution of the data itself and tells you how likely a given example is. For example, models that predict the next word in a sequence are typically generative models (usually much simpler than GANs) because they can assign a probability to a sequence of words. 20
  • 22. Supervised Machine Learning ● Data : where and either (regression) or where ● Model , in general it is a non-linear function. ● Loss function : Quantifies the mismatch between the actual output and predicted output , ● Training : Minimize the loss against the weights / parameters of the model. 22
  • 23. Common Loss functions ● Mean Squared Error (regression) = , (for linear cases) ● Cross Entropy (classification) + ● Activation (non-linear) function: Sigmoid : p(X) = ( ∗ ) 23
  • 24. 24
  • 26. Optimization ● Supervised machine learning is all about finding the model parameters or ‘weights’ which can represent the non-linear mapping between the input (features) and the output. ● Finding a set of parameters which minimizes the ‘mismatch’ or loss between the actual output and predicted output is called ‘optimization’. ● There are many optimization schemes and one of the most common is ‘gradient descent’. 26
  • 27. Gradient descent ● It is an optimization scheme to find the model parameters iteratively by minimizing the loss function 27
  • 29. 29
  • 32. Two key properties of artificial neural networks
  • 33. 33
  • 37. Challenges in modeling text ● Computers are good in numerical computation / number crunching ● Numerical operations (+,-,x,/) are not possible on text. ● There is way to get relations like the following one. King – Man + Women = Queen ! 37
  • 38. Vectorization / Latent space ● Let us consider the text : Data = “quick brown fox jumped over the lazy dog “ ● Assign unique id to each word/symbol and build a vocabulary. ● Now represent each word with a vector (one hot encoding) of the size of the vocabulary. ● Unfortunately, the dimensionality of the vector is very high and all the entries except one are zeroes. 38
  • 39. Word Embedding ● Let us consider a one hot encoded vector X N is the size of the vocabulary. ● We can find a matrix such that Here ● In common English used we have around 40,000 words (N=40,000) and we generally have M = 300. ● There are many pre-trained models to get vectorizd form of words, such as Glove and Word2Vec 39
  • 41. 41
  • 42. 42
  • 44. (1) Seq2Seq Model 44 “The encoder processes each item in the input sequence, it compiles the information it captures into a vector (called the context). After processing the entire input sequence, the encoder sends the context over to the decoder, which begins producing the output sequence item by item.” RNN (LSTM) Encoder-Decoder
  • 49. 49
  • 50. 50
  • 51. Responsible AI ● Explainable AI ● Safe AI ● Fair AI / Unbiased 51
  • 54. References 1. A high-bias, low-variance introduction to Machine Learning for physicists 2. Statistical Mechanics of deep learning 3. Discovering Physical Concepts with Neural Networks 4. Physics-informed machine learning 5. On scientific understanding with artificial intelligence 6. AI Feynman: A physics-inspired method for symbolic regression 7. Defining physicists’ relationship with AI 8. Machine intelligence – Nature insight 9. Rise of the Machines – Science special issue 10.https://prasad-jayanti.medium.com/ eargatisticanicee 54