Course12710877865 lectures
Machine Learning for Core Engineering Disciplines
Prof. Ananth Govind Rajan · IISc Bangalore
About
This course will introduce students and practitioners of core engineering disciplines to the fundamentals and applications of machine learning. The course will cover the following material: introduction to data science and machine learning, examples of supervised/unsupervised/reinforcement learning, motivation for machine learning with examples derived from various core engineering disciplines; introduction to Python, scientific computing packages (NumPy, SciPy, Matplotlib), and simple ML packages (Scikit-learn, Pytorch); linear and nonlinear regression, confidence intervals and goodness of fit, loss functions, gradient descent algorithm, overfitting/underfitting, regression/classification learning; clustering algorithms, singular-value decomposition, principal component analysis, and nonlinear dimensionality reduction; decision trees and ensemble methods, boosting and bagging techniques, random forests, gradient-boosted machine learning, support vector machines, Gaussian process regression; hyperparameter tuning and cross validation; introduction to neural networks and deep learning; feed-forward, convolutional, and recurrent neural networks
Intended audience: Core Engineering Disciplines
Lectures
Week 1 Introduction
- Introduction to Data Science, Artificial Intelligence, and Machine Learning
- Fundamentals of Machine Learning
- Probability and Statistical Foundations for Machine Learning - I
- Probability and Statistical Foundations for Machine Learning - II
- Probability Distributions for Discrete and Continuous Random Variables
Week 2 Fundamentals of Statistics and Data Interpretation
- Transforming Random Variables and Their Distributions
- Understanding Population and Sample Statistics - I
- Understanding Population and Sample Statistics - II
- Multivariate Linear Regression and Model Evaluation
- Hypothesis Testing and Confidence Intervals: Z-Test and T-Test
Week 3 Regularization for Model Generalization and Performance
- Overfitting, Underfitting, and Ridge Regression
- LASSO and Elastic Net Regularization Techniques
- Bias-Variance TradeOff in Machine Learning
- Logistic Regression and Evaluation of Binary Classification Models
- ROC Analysis and Multiclass Classification
Week 4 Loss Functions and Model Evaluation
- Tutorial - I (Introduction to Python)
- Loss Functions - I
- Loss Functions - II
- Loss Functions - III
- Loss Function - IV
Week 5 Gradient Descent and Related Algorithms for Training ML Models
- Training ML Models: Gradient Descent
- Training ML Models: Gradient Descent and Hessian Matrix Analysis
- Practical Aspects of ML Model Training and Stochastic Gradient Descent
- Variants of Stochastic Gradient Descent for ML Model Training
- Gradient Descent Applied to Toy Quadratic Regression
Week 6 Model Training, Validation, Optimization, and Unsupervised Learning
- Cross Validation in Machine Learning
- Hyperparameter Tuning for ML Models
- Tutorial - II (Linear Regression using Python)
- Tutorial - III (Ridge and LASSO Regression, Cross Validation and Hyperparameter tuning using Python)
- Unsupervised Learning: Principal Component Analysis (PCA)
Week 7 Unsupervised Learning: Clustering and Dimensionality Reduction
- Singular Value Decomposition and PCA
- Fundamentals of Clustering with K-means
- Advanced Clustering Techniques
- Nonlinear Dimensionality Reduction Techniques -I
- Nonlinear Dimensionality Reduction Techniques -II
Week 8 Decision Trees and Ensemble Methods - I
- Unsupervised Learning on Toy Datasets
- Decision Trees in Supervised ML
- Decision Trees for Regression and Classification
- Classification using Simple Decision Trees
- Ensemble Learning
Week 9 Decision Trees and Ensemble Methods - II
- Random Forest and Boosting of Decision Trees
- Adaptive Boosting (AdaBoost)
- Unsupervised Learning in Python (Tutorial 1)
- Unsupervised Learning in Python (Tutorial 2)
- Gradient Boosted Decision Trees and Advanced Boosting Libraries
Week 10 Advanced Supervised Learning and Kernel Methods
- Decision Stump
- Support Vector Machines (SVM)
- Mathematics of SVM Margins
- Support Vector Regression (SVR)
- Kernel Ridge Regression (KRR)
Week 11 Deep Learning and Neural Network
- Gaussian Process Regression (GPR)
- Supervised Machine Learning Tutorial with Python (Tutorial I)
- Supervised Machine Learning Tutorial with Python (Tutorial II)
- Supervised Machine Learning Tutorial with Python (Tutorial III)
- Introduction to Deep Learning and Neural Networks
Week 12 Advanced Neural Networks
- Overview of Advanced Neural Network Architectures: From CNNs to GANs and GNNs
- Mathematical Foundation and Activation Functions of Neural Networks
- Training an Artificial Neural Network: Forward Propagation, Backpropagation, and Hyperparameters
- Challenges in Training Neural Networks and their Mitigation
- Neural Network Challenges (Gradients, Overfitting) and Logic Gate Implementation
- Recurrent Neural Networks and Sequential Data Processing
- Graph Neural Networks and Generative AI Fundamentals
- Variational Autoencoders and Bayesian Generative Modeling
- Neural Networks with Tensorflow (Tutorial I)
- Neural Networks with Tensorflow (Tutorial II)
Syllabus and materials
At NPTEL, as the course publishes them.
Credits and licence
- Institution
- IISc Bangalore
- Department
- Multidisciplinary
- Teacher
- Prof. Ananth Govind Rajan
- Level
- Undergraduate
- Language
- English
- Subjects
- Computer science, 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
More like this
NPTEL101108661
Course
Drone Systems and Control
51 lectures · Source's player
NPTEL101108047
Course
Advanced Control System Design for Aerospace Vehicles
40 lectures · Video
NPTEL101108057
Course
Optimal Control, Guidance and Estimation
40 lectures · Video
NPTEL101108068
Course
Combustion in air breathing aero engines
62 lectures · Video
NPTEL101108086
Course
Gasdynamics: Fundamentals and Applications
65 lectures · Video
NPTEL103108127
Course
Trace and Ultra-Trace Analysis of Metals using Atomic Absorption Spectrometry
38 lectures · Source's player
NPTEL103108097
Course
Chemical Reaction Engineering
40 lectures · Video
NPTEL103108098
Course
Fundamentals of Transport Processes
40 lectures · Video
NPTEL103108099
Course
Fundamentals of Transport Processes - II
40 lectures · Video
NPTEL103108100
Course
Modern Instrumental Methods of Analysis
43 lectures · Video
NPTEL103108123
Course
Transport Processes I: Heat and Mass Transfer
73 lectures · Video
NPTEL103108124
Course
Atomic and Molecular Absorption Spectrometry for Pollution Monitoring
41 lectures · Video