Learn · NPTEL

Course10810319248 lectures

Machine Learning and Deep learning - Fundamentals and Applications

Prof. M.K. Bhuyan · IIT Guwahati

Start with lecture 1 At NPTEL

About

In this course we will start with traditional Machine Learning approaches, e.g. Bayesian Classification, Multilayer Perceptron etc. and then move to modern Deep Learning architectures like Convolutional Neural Networks, Autoencoders etc. We will learn about the building blocks used in these Deep Learning based solutions. Specifically, we will learn about feedforward neural networks, convolutional neural networks, recurrent neural networks and attention mechanisms. On completion of the course students will acquire the knowledge of applying Machine and Deep Learning techniques to solve various real-life problems.

Intended audience: UG, PG and PhD students and industry professionals who want to work in Machine and Deep Learning.

Prerequisites: Knowledge of Linear Algebra, Probability and Random Process, PDE will be helpful.

Lectures

Week 1: Introduction

  1. Lec 1: Introduction to Machine Learning YouTube
  2. Lec 2: Performance Measures of Classification YouTube
  3. Lec 3: Bias-Variance Tradeoff YouTube
  4. Lec 4: Regression YouTube

Week 2: Bayesian Decision Theory

  1. Lec 5: Bayesian Decision Theory (Part I) YouTube
  2. Lec 6: Bayesian Decision Theory (Part II) YouTube
  3. Lec 7: Bayes Decision Theory - Binary Features (Part III) YouTube
  4. Lec 8: Bayesian Decision Theory (Part IV) YouTube
  5. Lec 9: Bayesian Decision Theory (Part V) YouTube
  6. Lec 10: Bayesian Belief Networks YouTube

Week 3- Parametric Approaches and Non- Parametric Density Estimation

  1. Lec 11: Parameter Estimation and Maximum Likelihood Estimation YouTube
  2. Lec 12: Parameter Estimation and Bayesian Estimation YouTube
  3. Lec 13: Concept of non-parametric techniques YouTube
  4. Lec 14: Density Estimation by Parzen Window YouTube
  5. Lec 15: Parzen Window and K nearest neighbor algorithm YouTube

Week 4: Perceptron Criteria and Discriminative Models

  1. Lec 16: Linear Discriminant Functions and Perceptron Criteria (Part I) YouTube
  2. Lec 17: Linear Discriminant Functions and Perceptron Criteria (Part II) YouTube
  3. Lec 18: Linear Discriminant Functions and Perceptron Criteria (Part III) YouTube
  4. Lec 19: Support Vector Machine (Part I) YouTube
  5. Lec 20: Support Vector Machine (Part II) YouTube

Week 5: Logistic Regression, Decision Trees and Hidden Markov Model

  1. Lec 21: Logistic Regression YouTube
  2. Lec 22: Decision Tree YouTube
  3. Lec 23: Hidden Markov Model (HMM) YouTube

Week 6 - Ensemble Methods

  1. Lec 24: Ensemble Classifiers (Part I) YouTube
  2. Lec 25: Ensemble Classifiers (Part II) YouTube

Week 7: Dimensionality Problem

  1. Lec 26: Dimensionality Problem and Principal Component Analysis YouTube
  2. Lec 27: Principal Component Analysis YouTube
  3. Lec 28: Linear Discriminant Analysis (LDA) (Part I) YouTube
  4. Lec 29: Linear Discriminant Analysis (LDA) (Part II) YouTube

Week 8: Mixture Model and Clustering

  1. Lec 30: Gaussian Mixture Model and EM Algorithm YouTube
  2. Lec 31: K-means clustering YouTube

Week 9: Clustering

  1. Lec 32: Fuzzy K-means clustering YouTube
  2. Lec 33: Hierarchical Agglomerative Clustering and Mean-shift Clustering YouTube

Week 10: Artificial Neural Network

  1. Lec 34: Artificial Neural Networks for Pattern Classification (PART 1) YouTube
  2. Lec 35: Artificial Neural Networks for Pattern Classification (PART 2) YouTube
  3. Lec 36: Artificial Neural Networks for Pattern Classification (PART 3) YouTube

Week 11: Introduction to Deep Neural Networks

  1. Lec 37: Introduction to Deep Learning and Convolutional Neural Network (CNN) YouTube
  2. Lec 38: Vanishing and Exploding Gradients in Deep Neural Networks YouTube
  3. Lec 39: CNN Architectures - LeNet-5 and AlexNet YouTube
  4. Lec 40: CNN Architectures – VGG 16, GoogLeNet and ResNet YouTube

Week 12: Recent Trends in Deep Learning

  1. Lec 41:Generative Adversarial Networks (GAN) - Fundamentals and Applications YouTube
  2. Lec 42: U-Net: Convolutional Networks for Image Segmentation YouTube
  3. Lec 43: Introduction to Autoencoder and Recurrent Neural Networks (RNN) YouTube
  4. Lec 44: Programming Concepts YouTube
  5. Lec 45: Programming Concepts YouTube
  6. Lec 46: Problem Solving Session YouTube
  7. Lec 47: Problem Solving Session YouTube
  8. Lec 48: Problem Solving Session YouTube

Syllabus and materials

At NPTEL, as the course publishes them.

Credits and licence

Institution
IIT Guwahati
Department
Electrical Engineering
Teacher
Prof. M.K. Bhuyan
Level
Undergraduate
Language
English
Subjects
Engineering
Source
NPTEL
Licence
CC BY-NC-SA, as NPTEL states it. Non-commercial use only. NPTEL's terms
Attribution
NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
Who can watch
NPTEL gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed