Deep Learning

B.Tech Course Scheme

Course Materials (PPTs/PDFs/Handouts):

2025 

B.Tech IT Sem 7 Deep Learning (DJS22ITC7014) [ UG Syllabus ]

1. Fundamentals of Deep Learning

1. • Introduction to Neural Networks PDF

   • Learning through Basic NN Spreadsheet

   • Error Backpropagation NN Training Spreadsheet

   • Introduction to Deep Learning PDF

2. Supervised Learning with Feedforward Neural Networks

1. • Feedforward Neural Networks

   • Backpropagation

   • Optimization Techniques

   • Regularization

3. Regularization and Model Tuning

1. • Overfitting and Underfitting

   • Regularization Techniques

   • Model Tuning

4. Convolutional Neural Networks (CNN)

1. • CNN Architecture

   • Convolution Operations

   • Feature Extraction

   • Popular CNN Architectures

   • Applications

5. Sequence Modelling

1. • Recurrent Neural Networks (RNN)

   • Backpropagation Through Time (BPTT)

   • Variants of RNN

   • Applications

6. Unsupervised Learning and Dimensionality Reduction

1. • Kohonen Self-Organising

   • Autoencoders

   • Variational Autoencoders (VAE)

2022 

B.Tech IT Sem 6 IT315 Deep Learning [ UG Syllabus ]

1. Introduction

1. • Introduction to Neural Networks PDF Oct 2022

   • Learning through Basic NN Spreadsheet Nov 2022

   • Error Backpropagation NN Training Spreadsheet

   • Introduction to Deep Learning PDF Nov 2022

2. Performance Evaluation

1. • Model Evaluation (Regularization) PDF

   • Model Improvement (Ensemble Learning) PDF Nov 2022

   • Optimizers in Deep Learning PDF Nov 2022

3. Supervised Deep Learning: CNN

1. • Convolutional Neural Networks PDF Nov 2022

4. Supervised Deep Learning: RNN

1. • Recurrent Neural Network PDF Nov 2022

5. Unsupervised Deep Learning

1. • Generative Adversarial Networks (GAN) PDF

   • Autoencoders PDF

6. Applications PDF

Lab Experiments

• Guidelines for writing DL Lab Experiments - Jan 2023 [ PDF ]

• Introduction to NN

  • Lab 1: Understanding AND, OR, NAND and XOR problem with basic ANN [ Lab1.ipynb ]

  • Lab 2: Implementation and training NN with 2 inputs to learn AND, OR, NAND and XOR functions [ Lab2.ipynb ]

  • Lab 3: Implementation and training NN with 3 inputs to learn AND, OR, NAND and XOR functions [ Lab3.ipynb ]

• Convolutional Neural Network

  • Lab4: Convolution Layer and Pooling Layer [ Lab4.ipynb ]

  • Lab 5:  Implement Digit Recognition using Deep Learning

    • Implementation of LeNet-5 Using Keras [ Lab5.ipynb ]

• Performance Evaluation

• Lab 6:  Lab MI using Regularization [ Lab6.ipynb ]

• Lab 7:  Model Improvement using Dropout [ Lab7.ipynb ]

• Lab 8:  Model Improvement using Data Augmentation and Early Stopping [ Lab8.ipynb ]

  • Confusion Matrix [ Confusion Matrix Lab.ipynb ]

    • Confusion Matrix Example [ Spreadsheet.xls ]

    • Confusion Matrix Example [ PDF ]

    • Example: Multiclass Confusion Matrix [ PDF ]

• Optimization

• Lab 9:  Implement optimization algorithm [ Lab9.ipynb ]

• Lab9a Adam Optimizer.ipynb [Lab9a.ipynb

• Recurrent Neural Network (RNN)

  • Lab 10: Implementation of RNN with Keras [ Lab10.ipynb ]

  • Lab11: Implementation LSTM to  Predict Stock Prices [ Lab11.ipynb ]

  • Lab12: Image Captioning [ Lab12.ipynb ]

• Generative Adversarial Networks

  • Lab 13:  Text-to-Image Stable Diffusion Model .ipynb [ Lab13.ipynb ]

• Autoencoders

  • Lab 14:  Create an autoencoder to reconstruct image.ipynb [ Lab 14.ipynb ]

Lab Manual

• Sample Gray Scale 8-bit BMP Images for experiment [ IMAGE FOLDER ]

• Guidelines for writing DL Lab Experiments - Jan 2023 [ PDF ]

• Deep Learning using Python = Lab Manual - July 2020 [ PDF ]

  • Lab 1 [ PDF ]

Course Examination and Evaluation

• 2023-24

  • Internal Assessments

    • IA-1: [ IA-1 QP PDF ]        [ IA-1 Solution PDF ]

    • IA-2: [ IA-2 QP PDF ]        [ IA-2 Solution PDF ]

  • Assignments: 

    • Assignment #1: QP PDF     [ Solution PDF ] 

    • Assignment #2: QP PDF     [ Solution PDF ]

  • Theory Examination 06May2023 

    • Theory QP PDF    [ TH Solution PDF ]  

• 2022-23

  • Internal Assessments

    • IA-1: [ IA-1 QP PDF ]        [ IA-1 QP Solution PDF ]

    • IA-2: [ IA-2 QP PDF ]        [ IA-2 Solution PDF ]

  • Assignments: 

    • Assignment #1: QP PDF     [ Solution PDF ] 

    • Assignment #2: QP PDF     [ Solution PDF ]  

  • Practice Quiz #1 [ Google Form ]

  • Theory Examination 06May2023 

    • Theory QP PDF    [ TH Solution PDF ]  

• Talk in STTP

  • Session 1: GANs for Medical Image Processing [ LaTeX PDF ]

  • Session 2: GANs for Medical Image Processing [ LaTeX PDF ]

  • Session 3: DICOM Medical Image Processing [ .ipynb ]

  • Session 3: GAN over MNIST [ .ipynb ]

  • Session 3: GAN for Image Synthesis over IXI dataset [ .ipynb ]

Old Course Materials (PPTs/PDFs/Handouts)

M.Tech Course Scheme

• M.Tech IT Sem 6 [ Scheme ]

• IT517T Deep Learning [ PG Syllabus ]

Course Materials (PPTs/PDFs/Handouts):

• • Introduction

    • Introduction to Neural Networks - 15 Oct 2022 [ PDF ]

      • Learning through Basic NN Nov 2022 - [ Spreadsheet ]

    • Introduction to Deep Learning - 20 Nov 2022 [ PDF ]

  • Performance Evaluation

    • Model Evaluation (Regularization) [ PDF ]

    • Model Improvement (Ensemble Learning) - 25 Nov 2022 [ PDF ]

    • Optimization - 25 Nov 2022 [ PDF ]

  • Supervised Deep Learning: CNN

    • Convolutional Neural Networks 25 Nov 2022 [ PDF ]

  • Supervised Deep Learning: RNN

    • Recurrent Neural Network 26 Nov 2022 [ PDF ]

  • Unsupervised Deep Learning

    • Generative Adversarial Networks (GAN)  [ PDF ]

    • Autoencoders  [ PDF ]

  • Applications

    • 
      

Lab Experiments

• Guidelines for writing DL Lab Experiments - Jan 2023 [ PDF ]

• Introduction to NN

  • Lab 1: Understanding AND, OR, NAND and XOR problem with basic ANN [ Lab1.ipynb ]

  • Lab 2: Implementation and training NN with 2 inputs to learn AND, OR, NAND and XOR functions [ Lab2.ipynb ]

  • Lab 3: Implementation and training NN with 3 inputs to learn AND, OR, NAND and XOR functions [ Lab3.ipynb ]

• Convolutional Neural Network

  • Lab4: Convolution Layer and Pooling Layer [ Lab4.ipynb ]

  • Lab 5:  Implement Digit Recognition using Deep Learning

    • Implementation of LeNet-5 Using Keras [ Lab5.ipynb ]

• Performance Evaluation

• Lab 6:  Lab MI using Regularization [ Lab6.ipynb ]

• Lab 7:  Model Improvement using Dropout [ Lab7.ipynb ]

• Lab 8:  Model Improvement using Data Augmentation and Early Stopping [ Lab8.ipynb ]

• Lab 9:  Implement optimization algorithm [ Lab9.ipynb ]

• Recurrent Neural Network (RNN)

  • Lab 10: Implementation of RNN with Keras [ Lab10.ipynb ]

  • Lab11: Implementation LSTM to  Predict Stock Prices [ Lab11.ipynb ]

• Generative Adversarial Networks

  • Lab 11: 

• Autoencoders

  • Lab 12: 

Lab Manual

• Sample Gray Scale 8-bit BMP Images for experiment [ IMAGE FOLDER ]

• Guidelines for writing DL Lab Experiments - Jan 2023 [ PDF ]

• Deep Learning using Python = Lab Manual - July 2020 [ PDF ]

  • Lab 1 [ PDF ]

Course Examination and Evaluation

• 2023-24

  • Internal Assessments

    • IA-1: [ IA-1 QP PDF ]        [ IA-1 QP Solution PDF ]

    • IA-2: [ IA-2 QP PDF ]        [ IA-2 Solution PDF ]

  • Assignments: 

    • Assignment #1: QP PDF     [ Solution PDF ] 

• M. Tech 2022-23

  • Internal Assessment #1: [ IA1 QP PDF ]  

  • Assignment #1 : [ Assign1 Question PDF ]  

  • Practice Quiz #1 [ Google Form ]

  • Theory Examination [ June 2023 QP PDF ]

•