Artificial Intelligence and Machine Learning for Industry (Batch 8)

The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator

Motivations and Introduction to different ML Paradigm 

Linear Algebra for ML 

• Vectors and Matrices

• Vector Space and Subspace

• System of Linear Equations

• The Concept of Rank and Independent Vectors

• Inner Product Space

• Norms, Positive Definite Matrix

• Matrix factorisation (EVD, SVD, QR, LR, etc.)

• Projection and Orthogonality

Probability and Statistics for Data science

• Random Variables

• Distribution and Density Functions

• Conditional Probability, Bayes Theorem

• Joint Distribution

• Concept of Independence, Covariance, and Correlation

• Introductory Statistical Inference (Likelihood, MAP, etc.)

• Concept of Entropy

• Mutual Information, and KL Divergence

Optimisation

• Function and Derivatives

• Gradient Descent

• Stochastic Gradient Descents

• Convex Optimisation 

• Formulation and Optimality Conditions

• ADAM Optimiser

Hands-on Demo 1: Linear Algebra using NumPy

• Concepts of Linear Algebra and Probability Basics 

• Optimisations with Practical ML Applications

Learning Outcome

Learners will develop a comprehensive understanding and application of linear algebra concepts, probability and statistics, and optimisation in real-world machine learning tasks.

The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator

• 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, Regularisation and Bias-Variance Trade-off 

• M2 Project: Regression application   

Learning Outcome

Learners will master simple and multiple linear regression, non-linear regression, and the least squares approach, gaining practical experience through hands-on demos. They will also learn model selection, regularization, and the bias-variance trade-off, culminating in a regression application project discussion.

The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator

Motivation and Introduction to Classification Problems 

Logistic Regression

• Logistic Regression

• Hands-on Demo 4: Logistic Regression

Decision Tree

• Introduction to Decision Trees

• Random Forests, Bagging, and Boosting

• Hands-on Demo 5: Random Forests

• Interpretability of Machine Learning Models

Hyperplanes

• Concept of Hyperplane Classifier 

SVM

• Support Vector Machines, Kernel SVM

• Hands-on Demo 6: SVM

• Multi-class Classifiers

Clustering

• Clustering Methods

• Hands-on Demo 7: Clustering

Project

• Classification Application

Learning Outcome

Learners will develop expertise in logistic regression, decision trees, random forests, and support vector machines, gaining practical experience through hands-on demos. The will also learn clustering methods and the interpretability of machine learning models, culminating in a classification application project discussion.

The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator

Neural Networks

• Fundamentals of Neural Network and Feedforward Network

• Concept of Training and Backpropagation

• Hands-on Demo 8: ANN

Convolutional Neural Networks

• Fundamentals of Convolution

• Convolutional Neural Network Architecture

• Hands-on Demo 9: CNN

Recurrent Neural Networks/LSTM

• Introduction to Time Series and Sequential Data

• Introduction to Language Modelling and NLP

• Recurrent Neural Network and LSTM/GRU

• Hands-on Demo 10

Graph Neural Networks

• Introduction to Graph Data

• Graph Neural Network Architecture

• Hands-on Demo 11

Learning Outcome

Master the fundamentals of neural networks, including feedforward networks, training, and backpropagation, with practical experience through hands-on demos. Additionally, learn advanced topics such as convolutional neural networks, recurrent neural networks, graph neural networks, transformers, and generative AI, applying these concepts to real-world applications.

The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator

Transformers

• Core mechanics — self-attention, positional encodings, causal mask

• Efficiency & fine-tuning — Flash/linear attention, LoRA-FT/adapters

• Multimodal extensions — vision-language models

Generative AI

• Autoencoder, Variational Autoencoders, Generative Adversarial Networks (GANs)

• Diffusion for images and text modalities

 LLM Alignment

• Alignment pipeline — SFT → reward model → RLHF/DPO/PPO

• Alternative approaches — Constitutional AI, RLAIF 

The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator

1. Linear Regression Lab

• Is there a connection between sales and different types of ad expenditure? In this lab, we try to forecast the sales of a product assuming ad sales are available.

2. Logistic Regression Lab

• Sentiment Analysis of consumers. Can we directly infer the quality of any product based on its reviews?

3. Decision Tree, Random Forest, XGBoost

• In-depth analysis of algorithms on benchmark datasets. 

4. Support Vector Machines

• Image classification on fashion MNIST dataset, intuition of soft margin, hard margin, solving SVM using CVXPY

5. Neural networks

• Basic understanding and implementation of each layer of NN. Writing and understanding gradient descent/backpropagation algorithm in Python

• Comparison of Neural Networks and SVM on image classification datasets

6. Convolutional Neural Networks (CNN)

• Ever wondered how computers identify faces? We will see how CNN has revolutionized the field of Computer Vision

• Understanding layers, visualization of the learning process, Occlusion, GRADCAM

7. Sequential Model (Recurrent Neural Network/Long Short-Term Memory)

• Implementation of RNN/LSTM. Hands-on implementation for Caption/Summary generation from images/videos.

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

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

10. Graph Neural Network

• Are you ready to take your machine learning to the next level? Whether you want to build a recommender system for social media platforms or do drug prediction in biomedical, GNN has your back. We will see the Extension of Deep Learning on Graphs (GNN).

• Introduction to several GNN variants GCN, GraphSage, etc

11. Natural Language Processing

• Text Summarisation

12. Generative AI

• Fine-Tuning SLMs and LLMs and Their Integration with Downstream Tasks

13. Course Project

• Build your own recommender system using any of the discussed techniques (GNN, CNN, LSTM, classical ML, etc.)

Faculty will be conducting Q&A/Doubt-clearing sessions twice a month.

• Each lecture is accompanied by a hands-on demo session along with a student project. (Hands-on demo session are a part of 110 hours.)  

• There will be following for doubt clearance and discussion sessions during and after the programme as well.  

• There will be 2 modes of interaction for the learners:

  • A telegram announcement group where they are only recipients and cannot see the other participants’ contact details/names. This group will be primarily used by the programme coordinator for making any and every programme-related announcement to the learners.

  • A discussion forum on the LMS for posting all their academic queries and conducting academically engaging discussions. These posts, if queries, will be replied to by the faculty & TAs. The faculty team can also post questions to engage the learners as required.

Any science, engineering, or commerce graduate / Diploma holders (10+3) or (10+2+3) are eligible to apply for this CEP, IIT Delhi AI ML course. Preference will be given to applicants with experience.

This CEP, IIT Delhi Artificial Intelligence and Machine Learning for Industry programme is designed for any fresh graduates from a science or engineering background seeking a career in the AI/ML domain, any professionals in the IT industry seeking to gain AI/ML expertise and become AI/ML specialists or any professionals seeking to upskill themselves and apply it in their strategic decision-making.

This CEP, IIT Delhi AI ML course is thoughtfully crafted with a special focus on learners from non-CS backgrounds. Contemporary case studies and practice sessions have been curated to provide hands-on experience in applying advanced machine-learning techniques to solve real-world problems.

The CEP, IIT Delhi Artificial Intelligence and Machine Learning for Industry is a Live course, and online sessions are delivered Direct-to-Device (D2D).

Yes, participants who score at least 50% marks overall and have a minimum attendance of 50% will receive a ‘Certificate of Completion’ and those who score less than 50% marks overall and have a minimum attendance of less than 50% will receive a ‘Certificate of Participation’ from CEP, IIT Delhi.

Here are some potential benefits of participating in this CEP, IIT Delhi AI and Machine Learning for Industry programme

• In-Depth Knowledge

• Practical Skills Development

• Industry-Relevant Curriculum

• Networking Opportunities

• Certification from a Prestigious Institution

• Career Advancement

• Access to Resources

• Knowledge of Industry Trends

• Opportunity for Collaborative Learning

• Access to Alumni Network

The scope of the CEP, IIT Delhi AI and Machine Learning for Industry in India is vast and transformative. With AI and ML driving innovations across sectors like healthcare, finance, e-commerce, and manufacturing, graduates are equipped to harness data-driven insights for business growth and efficiency. The programme emphasises practical applications through hands-on projects, industry collaborations, and mentorship by experts. Graduates are poised for roles in AI research, data science, consultancy, and leadership positions in companies adopting AI technologies. By leveraging, IIT Delhi's academic excellence and industry partnerships, the program prepares professionals to spearhead transformative AI initiatives in India's evolving market.

The IIT Delhi stands out as a premier choice for studying Artificial Intelligence and Machine Learning due to its esteemed faculty, cutting-edge research facilities, and industry collaborations. The program blends theoretical foundations with hands-on practical experience, preparing students to tackle real-world challenges in AI and ML applications across diverse sectors. With access to state-of-the-art labs, collaborative projects, and mentorship from leading experts, you gain valuable skills and insights that are highly sought-after in India's tech-driven economy. By choosing IIT Delhi for the AI and ML course, you open doors to a wealth of knowledge, resources, and career prospects in this rapidly evolving field.

If a student chooses to withdraw, they can do so within 15 days from the start of the program. In such cases, 80% of the total fee received will be refunded, excluding any applicable taxes paid. However, if the withdrawal occurs after this 15-day period, no refund will be applicable. To initiate withdrawal, students must email cepaccounts@admin.iitd.ac.in and icare@timespro.com stating their intent.