SlideShare uma empresa Scribd logo
1 de 35
Prof. Amlan Chakrabarti
IEEE Computer Soc. Dist. Vist. & ACM Dist. Speaker
Director, A.K.Choudhury School of Information Technology
University of Calcutta
National Webinar On Education 4.0 “Ensuring Continuity in Learning and Innovation Through Digitization”
Organized By: Singhad Institute of Management, Pune in Association with Savitribai Phule Pune University
12th June 2020
INTRODUCTORY CONCEPTS
Formal Definition
• “Machine learning is the field of study which gives the computers the ability to
learn without being explicitly programmed”- Arther Samuels 1959
• “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 Mitchells 1997
• Machine learning focuses on the development of computer programs that can
access data and use it learn for themselves.
• Example: To predict, traffic patterns at a busy intersection (task T)
• We can run it through a machine learning algorithm with data about past
traffic patterns (experience E)
• If it has successfully “learned”, it will then do better at predicting future traffic
patterns (performance measure P).
Defining The Learning Task
Why Machine Learning is Different?
Evolution of Machine Learning
Real World Problems lead to ML
• The goal of ML is never to make “perfect” guesses, the goal is to
make guesses that are good enough to be useful
Deep Learning in The Headlines
Deep Learning
9
Basics
• A deep neural network consists of a hierarchy of layers, whereby each
layer transforms the input data into more abstract representations
(e.g. edge -> nose -> face)
• The output layer combines those features to make predictions
Scene Labeling Using DL
Machine Learning for Smarter World
MACHINE LEARNING STRATEGIES
Machine Learning Techniques
• Supervised Learning
– Regression
– Classification
• Binary
• Multiclass
• Multi-label
• Unsupervised Learning
– Partitional
– Hierarchical
• Reinforcement
• Semi-Supervised
Supervised Learning
Supervised Learning: Regression
 There are a few concepts to unpack here:
• Dependent Variable
• Independent Variable(s)
• Slope & Intercept
• Error Function
Supervised Learning: Classification
Binary Classification
Multi-label Classification
Multiclass Classification
Unsupervised Learning
• No labels are given to the learning algorithm, leaving it on its own to
find structure in its input
• The goal of unsupervised learning is to find hidden patterns in
unlabeled data
Unsupervised Learning: Clustering
• Finding groups of objects such that objects in a group are similar (or
related) to one another and different from (or unrelated to) the objects in
other groups
Partitional Clustering Hierarchical Clustering
Applications of Clustering
Reinforcement Learning
• A technique to allow an agent to take actions and interact with an
environment so as to maximize the total rewards
• Similar to toddlers learning how to walk who adjust actions based on the
outcomes they experience
• A Playing Agent
– Manages to score a point it gets a +1 reward
– Each time it loses a point it gets a -1 penalty.
– it will iteratively update its policies so that the actions that bring rewards
are more probable and those resulting in a penalty are filtered out.
• The first application in which reinforcement learning gained notoriety was
when AlphaGo, a machine learning algorithm, won against one of the world’s
best human players in the game Go
Semi Supervised Learning
• Supervised Learning algorithm is a costly process, especially when
dealing with large volumes of data
• Unsupervised Learning is that it’s application spectrum is limited.
• Semi-supervised learning combines a small amount of labeled data
with a large amount of unlabeled data during training
• Application Scenarios: Speech Analysis, Internet Content
Classification, Protein Sequence Classification
Designing A Learning System
• Choose the training experience
• Choose exactly what is to be learned
– i.e. the target function
• Choose how to represent the target function
• Choose a learning algorithm to infer the target function from the
experience
NEURAL NETWORKS
 Massively parallel interconnected network of simple processing elements
which are intended to interact with the objects of the real world in the
same way as biological systems do.
 NN models are extreme simplifications of human neural systems.
Neural Networks
25
26
 In context of Machine Learning, we want to learn the parameters from the
training set, such that given the testing set data the training set can
correctly classify the instances
Artificial Neural Network (ANN)
ANN: Role of Weights & Bias
Adjusting Weights Adjusting Bias
ANN: Understanding the Layers
ANN: Forward & Backward Propagation
The Big Picture
ML in Practice
ML Platforms
Online Platforms Python Libraries
Future of Machine Learning
• As ML assumes increased importance in business applications, this
technology will be offered as a Cloud-based service known as Machine
Learning-as-a-Service (MLaaS)
• Connected AI systems will enable ML algorithms to “continuously learn,”
based on newly emerging information on the internet
• There will be a big rush among hardware vendors to enhance system
power to accommodate ML data processing. More accurately, hardware
vendors will be pushed to redesign their machines to do justice to the
powers of ML
• ML will help machines to work autonomously sense of context and
meaning of data
Machine Learning an Exploratory Tool: Key Concepts

Mais conteúdo relacionado

Mais procurados

ICT competencies of teachers
ICT competencies of teachersICT competencies of teachers
ICT competencies of teachersMart Laanpere
 
ICT Integrated Instruction: A Teaching Strategy
ICT Integrated Instruction: A Teaching StrategyICT Integrated Instruction: A Teaching Strategy
ICT Integrated Instruction: A Teaching Strategygenleosala
 
Computers in Education - ICT pedagogy in teacher education
Computers in Education - ICT pedagogy in teacher educationComputers in Education - ICT pedagogy in teacher education
Computers in Education - ICT pedagogy in teacher educationDr. I. Uma Maheswari Maheswari
 
ICT for Education - Successful Integration with Open Education Resources
ICT for Education - Successful Integration with Open Education Resources ICT for Education - Successful Integration with Open Education Resources
ICT for Education - Successful Integration with Open Education Resources Jacqueline Peters-Richardson
 
My Portfolio in EdTech2
My Portfolio in EdTech2My Portfolio in EdTech2
My Portfolio in EdTech2irishang
 
My Project in Educational Technology 2
My Project in Educational Technology 2My Project in Educational Technology 2
My Project in Educational Technology 2Lovely Apple Sallutan
 
My portfolio in Educational Technology 2
My portfolio in Educational Technology 2My portfolio in Educational Technology 2
My portfolio in Educational Technology 2Coleen Tolentino
 
Educational technology in the asia pacific region
Educational technology in the asia pacific regionEducational technology in the asia pacific region
Educational technology in the asia pacific regionroden_pg
 
Smart School Project
Smart School ProjectSmart School Project
Smart School ProjectXavier Chang
 
Role of ICT in examination
Role of ICT in examinationRole of ICT in examination
Role of ICT in examinationAhamed Yoonus S
 
Lesson 4 Educational Technology 2
Lesson 4 Educational Technology 2Lesson 4 Educational Technology 2
Lesson 4 Educational Technology 2Osmeña College
 
Role of ICT in Teaching Learning
Role of ICT in Teaching LearningRole of ICT in Teaching Learning
Role of ICT in Teaching LearningPravinGhosekar
 
National ICT Competency Standards for Teachers
National ICT Competency Standards for TeachersNational ICT Competency Standards for Teachers
National ICT Competency Standards for Teachersischool webboard
 
ICT for Teachers in Basic Education
ICT for Teachers in Basic EducationICT for Teachers in Basic Education
ICT for Teachers in Basic Educationischool webboard
 
A National ICT Competency Framework for Student Teachers
A National ICT Competency Framework for Student TeachersA National ICT Competency Framework for Student Teachers
A National ICT Competency Framework for Student TeachersJeroen Bottema
 
Portfolio in Educational Technology 2
Portfolio in Educational Technology 2Portfolio in Educational Technology 2
Portfolio in Educational Technology 2Esrin Depong
 

Mais procurados (20)

ICT competencies of teachers
ICT competencies of teachersICT competencies of teachers
ICT competencies of teachers
 
Visual Tools In Teaching Learning
Visual  Tools In Teaching LearningVisual  Tools In Teaching Learning
Visual Tools In Teaching Learning
 
ICT Integrated Instruction: A Teaching Strategy
ICT Integrated Instruction: A Teaching StrategyICT Integrated Instruction: A Teaching Strategy
ICT Integrated Instruction: A Teaching Strategy
 
Meaning of education technology
Meaning of education technologyMeaning of education technology
Meaning of education technology
 
Computers in Education - ICT pedagogy in teacher education
Computers in Education - ICT pedagogy in teacher educationComputers in Education - ICT pedagogy in teacher education
Computers in Education - ICT pedagogy in teacher education
 
ICT for Education - Successful Integration with Open Education Resources
ICT for Education - Successful Integration with Open Education Resources ICT for Education - Successful Integration with Open Education Resources
ICT for Education - Successful Integration with Open Education Resources
 
My Portfolio in EdTech2
My Portfolio in EdTech2My Portfolio in EdTech2
My Portfolio in EdTech2
 
My Project in Educational Technology 2
My Project in Educational Technology 2My Project in Educational Technology 2
My Project in Educational Technology 2
 
My portfolio in Educational Technology 2
My portfolio in Educational Technology 2My portfolio in Educational Technology 2
My portfolio in Educational Technology 2
 
Educational technology in the asia pacific region
Educational technology in the asia pacific regionEducational technology in the asia pacific region
Educational technology in the asia pacific region
 
Pedagogy and ICT
Pedagogy and ICTPedagogy and ICT
Pedagogy and ICT
 
Smart School Project
Smart School ProjectSmart School Project
Smart School Project
 
Role of ICT in examination
Role of ICT in examinationRole of ICT in examination
Role of ICT in examination
 
Lesson 4 Educational Technology 2
Lesson 4 Educational Technology 2Lesson 4 Educational Technology 2
Lesson 4 Educational Technology 2
 
Role of ICT in Teaching Learning
Role of ICT in Teaching LearningRole of ICT in Teaching Learning
Role of ICT in Teaching Learning
 
National ICT Competency Standards for Teachers
National ICT Competency Standards for TeachersNational ICT Competency Standards for Teachers
National ICT Competency Standards for Teachers
 
ICT for Teachers in Basic Education
ICT for Teachers in Basic EducationICT for Teachers in Basic Education
ICT for Teachers in Basic Education
 
A National ICT Competency Framework for Student Teachers
A National ICT Competency Framework for Student TeachersA National ICT Competency Framework for Student Teachers
A National ICT Competency Framework for Student Teachers
 
Portfolio in Educational Technology 2
Portfolio in Educational Technology 2Portfolio in Educational Technology 2
Portfolio in Educational Technology 2
 
smart school
smart schoolsmart school
smart school
 

Semelhante a Machine Learning an Exploratory Tool: Key Concepts

Machine learning basics by akanksha bali
Machine learning basics by akanksha baliMachine learning basics by akanksha bali
Machine learning basics by akanksha baliAkanksha Bali
 
Machine learning basics
Machine learning basics Machine learning basics
Machine learning basics Akanksha Bali
 
Introduction to Machine Learning.pptx
Introduction to Machine Learning.pptxIntroduction to Machine Learning.pptx
Introduction to Machine Learning.pptxDr. Amanpreet Kaur
 
Lecture 5 machine learning updated
Lecture 5   machine learning updatedLecture 5   machine learning updated
Lecture 5 machine learning updatedVajira Thambawita
 
introduction to machine learning
introduction to machine learningintroduction to machine learning
introduction to machine learningJohnson Ubah
 
machine learning algorithm.pptx
machine learning algorithm.pptxmachine learning algorithm.pptx
machine learning algorithm.pptxSasmitaDash28
 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MAHIRA
 
Machine learning
Machine learningMachine learning
Machine learningAbrar ali
 
Intro/Overview on Machine Learning Presentation -2
Intro/Overview on Machine Learning Presentation -2Intro/Overview on Machine Learning Presentation -2
Intro/Overview on Machine Learning Presentation -2Ankit Gupta
 
Pattern recognition
Pattern recognitionPattern recognition
Pattern recognitionMinigranth
 
Machine Learning Contents.pptx
Machine Learning Contents.pptxMachine Learning Contents.pptx
Machine Learning Contents.pptxNaveenkushwaha18
 
unit 1.2 supervised learning.pptx
unit 1.2 supervised learning.pptxunit 1.2 supervised learning.pptx
unit 1.2 supervised learning.pptxDr.Shweta
 
It's Machine Learning Basics -- For You!
It's Machine Learning Basics -- For You!It's Machine Learning Basics -- For You!
It's Machine Learning Basics -- For You!To Sum It Up
 
Artificial Intelligence(Machine learning & deep Learning ).pptx
Artificial Intelligence(Machine learning & deep Learning ).pptxArtificial Intelligence(Machine learning & deep Learning ).pptx
Artificial Intelligence(Machine learning & deep Learning ).pptxAnil Kumar Prajapati
 
An Introduction to Machine Learning
An Introduction to Machine LearningAn Introduction to Machine Learning
An Introduction to Machine LearningVedaj Padman
 
Machine learning --Introduction.pptx
Machine learning --Introduction.pptxMachine learning --Introduction.pptx
Machine learning --Introduction.pptxvinivijayan4
 

Semelhante a Machine Learning an Exploratory Tool: Key Concepts (20)

Machine learning basics by akanksha bali
Machine learning basics by akanksha baliMachine learning basics by akanksha bali
Machine learning basics by akanksha bali
 
Machine learning basics
Machine learning basics Machine learning basics
Machine learning basics
 
Introduction to Machine Learning.pptx
Introduction to Machine Learning.pptxIntroduction to Machine Learning.pptx
Introduction to Machine Learning.pptx
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Lecture 5 machine learning updated
Lecture 5   machine learning updatedLecture 5   machine learning updated
Lecture 5 machine learning updated
 
introduction to machine learning
introduction to machine learningintroduction to machine learning
introduction to machine learning
 
AI Lesson 33
AI Lesson 33AI Lesson 33
AI Lesson 33
 
Lesson 33
Lesson 33Lesson 33
Lesson 33
 
machine learning algorithm.pptx
machine learning algorithm.pptxmachine learning algorithm.pptx
machine learning algorithm.pptx
 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
 
Machine learning
Machine learningMachine learning
Machine learning
 
Intro/Overview on Machine Learning Presentation -2
Intro/Overview on Machine Learning Presentation -2Intro/Overview on Machine Learning Presentation -2
Intro/Overview on Machine Learning Presentation -2
 
Pattern recognition
Pattern recognitionPattern recognition
Pattern recognition
 
Machine Learning Contents.pptx
Machine Learning Contents.pptxMachine Learning Contents.pptx
Machine Learning Contents.pptx
 
unit 1.2 supervised learning.pptx
unit 1.2 supervised learning.pptxunit 1.2 supervised learning.pptx
unit 1.2 supervised learning.pptx
 
It's Machine Learning Basics -- For You!
It's Machine Learning Basics -- For You!It's Machine Learning Basics -- For You!
It's Machine Learning Basics -- For You!
 
Artificial Intelligence(Machine learning & deep Learning ).pptx
Artificial Intelligence(Machine learning & deep Learning ).pptxArtificial Intelligence(Machine learning & deep Learning ).pptx
Artificial Intelligence(Machine learning & deep Learning ).pptx
 
An Introduction to Machine Learning
An Introduction to Machine LearningAn Introduction to Machine Learning
An Introduction to Machine Learning
 
Machine learning --Introduction.pptx
Machine learning --Introduction.pptxMachine learning --Introduction.pptx
Machine learning --Introduction.pptx
 
Machine learning
Machine learningMachine learning
Machine learning
 

Mais de achakracu

Lecture_IIITD.pptx
Lecture_IIITD.pptxLecture_IIITD.pptx
Lecture_IIITD.pptxachakracu
 
Lecture 4 01_2021
Lecture 4 01_2021Lecture 4 01_2021
Lecture 4 01_2021achakracu
 
Io t technologies_ppt-2
Io t technologies_ppt-2Io t technologies_ppt-2
Io t technologies_ppt-2achakracu
 
Role of ICT in Higher Education
Role of ICT in Higher EducationRole of ICT in Higher Education
Role of ICT in Higher Educationachakracu
 
Fundamentals of Quantum Computing
Fundamentals of Quantum ComputingFundamentals of Quantum Computing
Fundamentals of Quantum Computingachakracu
 

Mais de achakracu (6)

Lecture_IIITD.pptx
Lecture_IIITD.pptxLecture_IIITD.pptx
Lecture_IIITD.pptx
 
Lecture 4 01_2021
Lecture 4 01_2021Lecture 4 01_2021
Lecture 4 01_2021
 
Vecc day 1
Vecc day 1Vecc day 1
Vecc day 1
 
Io t technologies_ppt-2
Io t technologies_ppt-2Io t technologies_ppt-2
Io t technologies_ppt-2
 
Role of ICT in Higher Education
Role of ICT in Higher EducationRole of ICT in Higher Education
Role of ICT in Higher Education
 
Fundamentals of Quantum Computing
Fundamentals of Quantum ComputingFundamentals of Quantum Computing
Fundamentals of Quantum Computing
 

Último

Crushers to screens in aggregate production
Crushers to screens in aggregate productionCrushers to screens in aggregate production
Crushers to screens in aggregate productionChinnuNinan
 
Unit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfg
Unit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfgUnit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfg
Unit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfgsaravananr517913
 
Katarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School CourseKatarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School Coursebim.edu.pl
 
Internet of things -Arshdeep Bahga .pptx
Internet of things -Arshdeep Bahga .pptxInternet of things -Arshdeep Bahga .pptx
Internet of things -Arshdeep Bahga .pptxVelmuruganTECE
 
Configuration of IoT devices - Systems managament
Configuration of IoT devices - Systems managamentConfiguration of IoT devices - Systems managament
Configuration of IoT devices - Systems managamentBharaniDharan195623
 
Ch10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdfCh10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdfChristianCDAM
 
Industrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.pptIndustrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.pptNarmatha D
 
Main Memory Management in Operating System
Main Memory Management in Operating SystemMain Memory Management in Operating System
Main Memory Management in Operating SystemRashmi Bhat
 
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...Erbil Polytechnic University
 
multiple access in wireless communication
multiple access in wireless communicationmultiple access in wireless communication
multiple access in wireless communicationpanditadesh123
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvLewisJB
 
Arduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptArduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptSAURABHKUMAR892774
 
11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdf11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdfHafizMudaserAhmad
 
Energy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxEnergy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxsiddharthjain2303
 
complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...asadnawaz62
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...VICTOR MAESTRE RAMIREZ
 
National Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdfNational Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdfRajuKanojiya4
 
"Exploring the Essential Functions and Design Considerations of Spillways in ...
"Exploring the Essential Functions and Design Considerations of Spillways in ..."Exploring the Essential Functions and Design Considerations of Spillways in ...
"Exploring the Essential Functions and Design Considerations of Spillways in ...Erbil Polytechnic University
 
Virtual memory management in Operating System
Virtual memory management in Operating SystemVirtual memory management in Operating System
Virtual memory management in Operating SystemRashmi Bhat
 

Último (20)

Crushers to screens in aggregate production
Crushers to screens in aggregate productionCrushers to screens in aggregate production
Crushers to screens in aggregate production
 
Unit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfg
Unit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfgUnit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfg
Unit7-DC_Motors nkkjnsdkfnfcdfknfdgfggfg
 
Katarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School CourseKatarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School Course
 
POWER SYSTEMS-1 Complete notes examples
POWER SYSTEMS-1 Complete notes  examplesPOWER SYSTEMS-1 Complete notes  examples
POWER SYSTEMS-1 Complete notes examples
 
Internet of things -Arshdeep Bahga .pptx
Internet of things -Arshdeep Bahga .pptxInternet of things -Arshdeep Bahga .pptx
Internet of things -Arshdeep Bahga .pptx
 
Configuration of IoT devices - Systems managament
Configuration of IoT devices - Systems managamentConfiguration of IoT devices - Systems managament
Configuration of IoT devices - Systems managament
 
Ch10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdfCh10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdf
 
Industrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.pptIndustrial Safety Unit-IV workplace health and safety.ppt
Industrial Safety Unit-IV workplace health and safety.ppt
 
Main Memory Management in Operating System
Main Memory Management in Operating SystemMain Memory Management in Operating System
Main Memory Management in Operating System
 
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
 
multiple access in wireless communication
multiple access in wireless communicationmultiple access in wireless communication
multiple access in wireless communication
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvv
 
Arduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptArduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.ppt
 
11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdf11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdf
 
Energy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxEnergy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptx
 
complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...
 
National Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdfNational Level Hackathon Participation Certificate.pdf
National Level Hackathon Participation Certificate.pdf
 
"Exploring the Essential Functions and Design Considerations of Spillways in ...
"Exploring the Essential Functions and Design Considerations of Spillways in ..."Exploring the Essential Functions and Design Considerations of Spillways in ...
"Exploring the Essential Functions and Design Considerations of Spillways in ...
 
Virtual memory management in Operating System
Virtual memory management in Operating SystemVirtual memory management in Operating System
Virtual memory management in Operating System
 

Machine Learning an Exploratory Tool: Key Concepts

  • 1. Prof. Amlan Chakrabarti IEEE Computer Soc. Dist. Vist. & ACM Dist. Speaker Director, A.K.Choudhury School of Information Technology University of Calcutta National Webinar On Education 4.0 “Ensuring Continuity in Learning and Innovation Through Digitization” Organized By: Singhad Institute of Management, Pune in Association with Savitribai Phule Pune University 12th June 2020
  • 3. Formal Definition • “Machine learning is the field of study which gives the computers the ability to learn without being explicitly programmed”- Arther Samuels 1959 • “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 Mitchells 1997 • Machine learning focuses on the development of computer programs that can access data and use it learn for themselves. • Example: To predict, traffic patterns at a busy intersection (task T) • We can run it through a machine learning algorithm with data about past traffic patterns (experience E) • If it has successfully “learned”, it will then do better at predicting future traffic patterns (performance measure P).
  • 5. Why Machine Learning is Different?
  • 7. Real World Problems lead to ML • The goal of ML is never to make “perfect” guesses, the goal is to make guesses that are good enough to be useful
  • 8. Deep Learning in The Headlines
  • 9. Deep Learning 9 Basics • A deep neural network consists of a hierarchy of layers, whereby each layer transforms the input data into more abstract representations (e.g. edge -> nose -> face) • The output layer combines those features to make predictions
  • 11. Machine Learning for Smarter World
  • 13. Machine Learning Techniques • Supervised Learning – Regression – Classification • Binary • Multiclass • Multi-label • Unsupervised Learning – Partitional – Hierarchical • Reinforcement • Semi-Supervised
  • 15. Supervised Learning: Regression  There are a few concepts to unpack here: • Dependent Variable • Independent Variable(s) • Slope & Intercept • Error Function
  • 16. Supervised Learning: Classification Binary Classification Multi-label Classification Multiclass Classification
  • 17. Unsupervised Learning • No labels are given to the learning algorithm, leaving it on its own to find structure in its input • The goal of unsupervised learning is to find hidden patterns in unlabeled data
  • 18. Unsupervised Learning: Clustering • Finding groups of objects such that objects in a group are similar (or related) to one another and different from (or unrelated to) the objects in other groups Partitional Clustering Hierarchical Clustering
  • 20. Reinforcement Learning • A technique to allow an agent to take actions and interact with an environment so as to maximize the total rewards • Similar to toddlers learning how to walk who adjust actions based on the outcomes they experience • A Playing Agent – Manages to score a point it gets a +1 reward – Each time it loses a point it gets a -1 penalty. – it will iteratively update its policies so that the actions that bring rewards are more probable and those resulting in a penalty are filtered out. • The first application in which reinforcement learning gained notoriety was when AlphaGo, a machine learning algorithm, won against one of the world’s best human players in the game Go
  • 21. Semi Supervised Learning • Supervised Learning algorithm is a costly process, especially when dealing with large volumes of data • Unsupervised Learning is that it’s application spectrum is limited. • Semi-supervised learning combines a small amount of labeled data with a large amount of unlabeled data during training • Application Scenarios: Speech Analysis, Internet Content Classification, Protein Sequence Classification
  • 22. Designing A Learning System • Choose the training experience • Choose exactly what is to be learned – i.e. the target function • Choose how to represent the target function • Choose a learning algorithm to infer the target function from the experience
  • 24.  Massively parallel interconnected network of simple processing elements which are intended to interact with the objects of the real world in the same way as biological systems do.  NN models are extreme simplifications of human neural systems. Neural Networks
  • 25. 25
  • 26. 26
  • 27.  In context of Machine Learning, we want to learn the parameters from the training set, such that given the testing set data the training set can correctly classify the instances Artificial Neural Network (ANN)
  • 28. ANN: Role of Weights & Bias Adjusting Weights Adjusting Bias
  • 30. ANN: Forward & Backward Propagation
  • 33. ML Platforms Online Platforms Python Libraries
  • 34. Future of Machine Learning • As ML assumes increased importance in business applications, this technology will be offered as a Cloud-based service known as Machine Learning-as-a-Service (MLaaS) • Connected AI systems will enable ML algorithms to “continuously learn,” based on newly emerging information on the internet • There will be a big rush among hardware vendors to enhance system power to accommodate ML data processing. More accurately, hardware vendors will be pushed to redesign their machines to do justice to the powers of ML • ML will help machines to work autonomously sense of context and meaning of data

Notas do Editor

  1. Reinforcement: Learning through a reward mechnism Online: Doing something for every input you are getting Semi Supervised: Incorporates pseudo labelling Batch: Whole dataset at once