IIT Delhi Artificial Intelligence and Machine Learning for Industry

About Course

Artificial Intelligence and Machine Learning for Industry’ is a comprehensive course that provides participants with a foundational understanding of machine learning tools, algorithms, and their industrial applications. The course will equip participants with the knowledge and practical skills necessary to proficiently apply machine learning techniques to tackle complex problems across diverse domains such as sales and marketing, medical diagnostics, to sports analytics. The course is thoughtfully crafted with a fine balance between theory and practice, with a special focus on learners from non-CS backgrounds. Contemporary case studies and practice sessions have been curated to provide hands-on experience of applying advanced machine learning techniques, that are used by leading tech and non-tech companies (e.g., Google, Amazon, Coca-Cola, Flipkart, think tanks, Civil and Mechanical Engineering firms, Power companies, Government agencies, etc.).

Understanding of machine learning tools, algorithms, and industrial applications
Gain hands-on experience in applying advanced ML techniques through case studies and practice exercises
Understand the working of neural networks and gain the ability to design and implement them using various tools and techniques
Able to design and implement various AI and ML techniques in a range of real-world applications

Course Content

Module 1: Self-Paced Module – Practical Python for Industry Professionals

Foundations of Python Programming

Module 2: Mathematical Foundations for AI/ML

Module 3: Regression

Module 4: : Classification Methods

Module 5: Deep Learning

Projects

Linear Regression Lab
Logistic Regression Lab
Decision Tree, Random Forest, XGBoost
SVM
Neural networks
CNN
Sequential Model (RNN/LSTM)
Understanding and implementation of Variational AutoEncoder on MNIST dataset. We will see how to encode images in a latent space of lower dimensions.
Is it possible to generate new images which never existed? Understanding and implementation of Generative Adversarial Networks on benchmark datasets.
GNN
NLP
Course Project

About Course

What Will You Learn?

Course Content

Module 1: Self-Paced Module – Practical Python for Industry Professionals

Foundations of Python Programming

Module 2: Mathematical Foundations for AI/ML

Motivations and Introduction to different ML

Linear Algebra for ML

Probability and Statistics for Data science

Optimisation

Hands-on Demo 1: Linear Algebra using NumPy

Module 3: Regression

Simple and Multiple Linear Regression

Hands-on Demo 2: SLR/MLR

Least Squares Approach

Moving Beyond Linearity: Non-linear regression

Hands-on Demo 3: NLR

Model Selection

M2 Project – Regression application

Module 4: : Classification Methods

Motivation and Introduction to Classification Problems

Logistic Regression

Decision Tree

Hyperplanes

SVM

Clustering

M3 Project: Classification Application

Module 5: Deep Learning

Neural Networks

Convolutional Neural Networks

Recurrent Neural Networks/LSTM

Graph Neural Networks

Transformers

Generative AI

M4 Project – Deep learning application

Projects

Linear Regression Lab

Logistic Regression Lab

Decision Tree, Random Forest, XGBoost

SVM

Neural networks

CNN

Sequential Model (RNN/LSTM)

Understanding and implementation of Variational AutoEncoder on MNIST dataset. We will see how to encode images in a latent space of lower dimensions.

Is it possible to generate new images which never existed? Understanding and implementation of Generative Adversarial Networks on benchmark datasets.

GNN

NLP

Course Project

Tools to be taught The course focuses on the implementation of ML algorithms.

Python

PyTorch

Tensorflow

Sklearn

Pandas

NumPy

Matplotlib

Seaborn, and several popular libraries

Tools to be taught
The course focuses on the implementation of ML algorithms.