Major in

Machine Learning
Proposed by: Asst.Prof.A.K.Tripathi
 Proposed Name of Major Scheme and Credit Requirement

• Artificial Intelligence

Proposed Credits Requirement = 16

Credits to be earned from MOOC Swayam/NPTEL courses
Minimum course duration and credits: 8-12 weeks and 2/3 credits
 Proposed Courses from NPTEL
  Title of SWAYAN /     Name of Institute Duration of  Content-Type/
Sr  Credit(s)
NPTEL Course SME (Subject Matter Expert) Course ID offering course Course Category
No
  INTRODUCTION TO MACHINE    106106139  Department of
1 LEARNING PROF. BALARAMAN Computer Science      
RAVINDRAN IIT Madras 12 3 Elective/Video

  INTRODUCTION TO MACHINE    106105152  Department of CSE

  LEARNING PROF. SUDESHNA IIT Kharagpur
2    
SARKAR 2
8 Elective/Video

3 PRACTICAL MACHINE MR. ASHISH TENDULKAR, 106106213 Department of CSE

LEARNING WITH TENSORFLOW PROF. BALARAMAN Google
RAVINDRAN Department of CSE 8 2 Elective/Video
IIT Madras

4 MACHINE LEARNING FOR PROF. BALAJI 106106198 Department of CSE

ENGINEERING AND SCIENCE SRINIVASAN, IIT Madras 12 3 Elective/Video
APPLICATIONS PROF. GANAPTHY
KRISHNAMURTHI
5 MACHINE LEARNING, ML PROF. CARL GUSTAF 106106202 School of Electrical
JANSSON Engineering and
Computer Science
8 2 Elective/Video
KTH, The Royal
Institute Of
Technology
Progression and Courses to core industry areas
 Benefits of Taking Major in Machine Learning
 Progression of students to
 Placements
 Higher studies: M.Tech, MBA, MS, PhD
 Entrepreneurship
 Benefits to society and nation
 Progression to research
 Motivation for lifelong learning
 Machine Learning
Sr. Course Content Credit Duration
No
1. Introduction to Week 0: Probability Theory, Linear Algebra, Convex Optimization - (Recap) 3 12 weeks
Machine Learning Week 1: Introduction: Statistical Decision Theory - Regression, Classification, Bias
Variance
Week 2: Linear Regression, Multivariate Regression, Subset Selection, Shrinkage
Methods, Principal Component Regression, Partial Least squares
Week 3: Linear Classification, Logistic Regression, Linear Discriminant Analysis
Week 4: Perceptron, Support Vector Machines
Week 5:Neural Networks-Introduction, Early Models, Perceptron Learning,
Backpropagation, Initialization,Training & Validation, Parameter Estimation –
MLE, MAP, Bayesian Estimation
Week 6: Decision Trees, Regression Trees, Stopping Criterion & Pruning loss functions,
Categorical Attributes, Multiway Splits, Missing Values, Decision Trees –
Instability Evaluation Measures
Week 7: Bootstrapping & Cross Validation, Class Evaluation Measures, ROC curve,
MDL, Ensemble Methods - Bagging, Committee Machines and Stacking,
Boosting Week 8: Gradient Boosting, Random Forests, Multi-class
Classification, Naive Bayes, Bayesian Networks
Week 9: Undirected Graphical Models, HMM, Variable Elimination, Belief Propagation
Week10:Partitional Clustering, Hierarchical Clustering, Birch Algorithm, CURE
Algorithm, Density-based Clustering
Week 11: Gaussian Mixture Models, Expectation Maximization
Week 12: Learning Theory, Introduction to Reinforcement Learning, Optional videos
(RL framework, TD learning, Solution Methods, Applications)
 Machine Learning
Sr. Course Content Credit Duratio
No n

2. Introduction to Week 01 : Introduction: Basic definitions, types of learning, 2 8 weeks

machine learning hypothesis space and inductive bias, evaluation, cross-
validation.
Week 02 : Linear regression, Decision trees, overfitting
Week 03 : Instance based learning, Feature reduction, Collaborative
filtering based recommendation. Probability
Week 04 :Probability and Bayes learning
Week 05: Logistic Regression, Support Vector Machine, Kernel
function and Kernel SVM.
Week 06 : Neural network: Perceptron, multilayer network,
backpropagation, introduction to deep neural network.
Week 07 : Computational learning theory, PAC learning model,
Sample complexity, VC Dimension, Ensemble learning.
Week 08 :Clustering: k-means, adaptive hierarchical clustering,
Gaussian mixture model.
 Machine Learning
Sr. Course Content Credit Duration
No

3. Practical Week 1: Getting started with Tensorflow 2 8 weeks

machine Week 2: Overview of Machine Learning (Process and Techniques,
learning with Demonstration of ML concepts with Deep Playground)
tensorflow Week 3: Data Input and Preprocessing with Tensorflow
Week 4: Machine Learning Model Building
Week 5: Prediction with Tensorflow
Week 6: Monitoring and evaluating models using Tensorboard Week
7: Advance Tensorflow (Building custom models - CNNs,
Scaling up for large datasets)
Week 8: Distributed training with hardware accelerators
 Machine Learning
Sr.
Course Content Credit Duration
No

4. MACHINE Week 1 : Mathematical Basics 1 – Introduction to Machine Learning, Linear Algebra 3 12weeks
LEARNING FOR Week 2 : Mathematical Basics 2 -- Probability
ENGINEERING Week 3 : Computational Basics – Numerical computation and optimization,
AND SCIENCE Introduction to Machine Learning packages
APPLICATIONS Week 4 : Linear and Logistic Regression – Bias/Variance Tradeo, Regularization,
Variants of Gradient Descent, MLE, MAP, Applications
Week 5 : Neural Networks – Multilayer Perceptron, Backpropagation, Applications
Week 6 : Convolutional Neural Networks 1 – CNN Operations, CNN architectures
Week 7 : Convolutional Neural Networks 2 – Training, Transfer Learning,
Applications
Week 8 : Recurrent Neural Networks ¬– RNN, LSTM, GRU, Applications
Week 9 : Classical Techniques 1 – Bayesian Regression, Binary Trees, Random
Forests, SVM, Naïve Bayes, Applications
Week10 : Classical Techniques 2 – k-Means, kNN, GMM, Expectation Maximization,

Applications
Week 11 : Advanced Techniques 1 – Structured Probabilistic Models, Monte Carlo
Methods
Week 12 : Advanced Techniques 2 – Autoencoders, Generative Adversarial
Networks
 Machine Learning
Sr. Course Content Credit Duration
No
5. MACHINE Week 1: Introduction to the Machine Learning course 2 8 weeks
LEARNING, Week 2: Characterization of Learning Problems
ML Week 3: Forms of Representation
Week 4: Inductive Learning based on Symbolic Representations and Weak Theories
Week 5: Learning enabled by Prior Theories
Week 6: Machine Learning based Artificial Neural Networks
Week 7: Tools and Resources + Cognitive Science influences
Week 8: Examples, demos and exam preparations
Thank You