DA6401 Graduate ✓ Currently Offered

Introduction to Deep Learning

A comprehensive introduction to Deep Learning covering neural networks fundamentals, CNNs, RNNs, Transformers, and Generative Models

Course Overview

Semester
Spring 2026
Credits
12
Class Schedule
C Slot
Monday 10:00 am - 10:50 am
Tuesday 09:00 am - 09:50 am
Wednesday 08:00 am - 08:50 am
Friday 12:00 pm - 12:50 pm
Location
CRC302 & CRC103, IIT Madras
Semester Dates
January 19, 2026 – May 5, 2026 (Last Instruction Day)
Communication
Moodle will be the primary mode of communication for announcements. Students are expected to check Moodle regularly.
Lecture Mode
All lectures will be conducted in person. When an in-person class is not feasible, online lectures will be held and advance notice shall be provided with details. Missed classes (by the lecturer) will be compensated suitably.

Prerequisites

  • DA5000 - Mathematical Foundations of Datascience
  • DA5400 - Foundations of Machine Learning
  • Proficiency in Python programming

Course Description

This course provides a comprehensive introduction to Deep Learning. Beginning with the history of neural networks and the fundamental Perceptron, we move to modern Feedforward Neural Networks, training methodologies, and optimization techniques. The course covers specialized architectures including Convolutional Neural Networks (CNNs) for computer vision, Recurrent Neural Networks (RNNs) for sequence modeling, and Transformers for natural language processing. We conclude with advanced generative models such as GANs and Diffusion models.

Grading Scheme & Key Dates

ComponentWeightDate/Deadlines
Quiz 1 (MCQ)20%February 18, 2026
Quiz 2 (MCQ)20%March 25, 2026
Final Exam (Handwritten)40%May 8, 2026
Assignments (4 × 5%)20%See Assignment Schedule

Detailed Course Content

Module 1: Introduction & Fundamentals

  • Overview of Deep Learning: History, evolution, and success stories
  • Neural Fundamentals: McCulloch-Pitts Neuron, Threshold Logic
  • Perceptrons: Architecture, Learning Algorithm, and Limitations (XOR problem)
  • Multilayer Perceptrons (MLPs): Hidden layers, non-linearity, and Representation Power

Module 2: Feedforward Networks & Optimization

  • Computations: Sigmoid neurons, Automatic differentiation, Backpropagation derivation
  • Optimization: Gradient Descent (GD), Stochastic GD, Momentum, Nesterov, AdaGrad, RMSProp, and Adam
  • Initialization: Xavier and He initialization

Module 3: Regularization & Training Methodology

  • Bias-Variance Tradeoff, L2 Regularization, Early Stopping
  • Dataset Augmentation, Dropout, Injecting Noise
  • Practical Issues: Handling Class Imbalance, Domain Generalization

Module 4: Convolutional Neural Networks (CNNs)

  • Fundamentals: Image Processing, Convolution, stride, padding, pooling
  • Architectures: LeNet, AlexNet, VGGNet, GoogLeNet, ResNet
  • Advanced Training: Batch Normalization, Improved Activation Functions
  • Applications: Object Detection (R-CNN family, YOLO, SSD), Semantic Segmentation (U-Net)

Module 5: NLP & Sequence Models

  • Seq2Seq Tasks, Need for a different architecture
  • Embeddings: Word2Vec (Skip-gram/CBOW), Vector representations
  • RNNs: Backpropagation Through Time (BPTT), Vanishing/Exploding gradients
  • Gated Units: LSTMs and GRUs
  • Seq2Seq: Encoder-Decoder models (Overview), Introduction to Attention mechanisms

Module 6: Transformers & Generative Models

  • Transformers: Self-Attention (Multi-headed), Cross Attention, Positional Encoding
  • Modern Tokenization (BPE), Vision Transformers (ViT)
  • Generative Models: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs)
  • Diffusion Models & Introduction to Large Language Models (LLMs)

Lecture Materials

Module #TopicMaterialsAdditional Resources
1AIntroduction to Deep Learning and Artificial Neuron ModelsSlides
1BModern Neuron & MLPsSlides
2ABackpropagation in MLPsSlides
2BGradient DescentSlides
T1Practice Problems Set-ITutorial
Q1Quiz-ISet-ASet-BSet-C
2CAdaptive OptimizersSlides
3AIntroduction to Convolutional Neural NetworksSlides
Q2Quiz-IISet-ASet-BSet-C
4ASequence ModellingSlides
4BBPTTSlides
5AMachine Translation with RNNSlides
5BAttention & Transformers - 1Slides
5CAttention & Transformers - 2Slides
ESEnd SemesterSET-ASET-BSET-CKey

Programming Assignments

Assignments will be implemented in Python (NumPy/PyTorch). They are designed to complement the theoretical material without conflicting with quiz weeks.

AssignmentTopicDescriptionRelease DateDue Date
Assignment 1Multi-Layer Perceptron for Image ClassificationImplement a MLP and backpropagation from scratch using Numpy to classify MNIST digits.Feb 09, 2026 10:00 AMMar 08, 2026 23:59 PM
Assignment 2Building a Complete Visual Perception PipelineImplement a multi-task CNN in PyTorch to classify, bound, and segment pet images.Mar 21, 2026 00:00 AMApr 12, 2026 23:59 PM
Assignment 3Implementing a Transformer for Machine TranslationImplement a Transformer model for machine translation task (German to English).Apr 24, 2026 10:00 AMMay 19, 2026 23:59 PM

References

  • Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press
  • Dive into Deep Learning, Zhang et al. (Available online: d2l.ai)