Foundations of Deep Learning: Concepts and Applications

Lectures

Week 1 Introduction to Artificial Neural Networks

1. Overview of Machine Learning and Deep Learning Video
2. Single Layer Perceptron Video
3. Hands-on on Single Layer Perceptron Video
4. Multi-Layer Perceptron Video
5. Activation and Loss Functions Video

Week 2 Optimizers and Regularization Techniques

6. Gradient descent algorithm Video
7. Backpropagation in Neural Network Video
8. Varients of Gradient descent and Momentum based techniques Video
9. Regularization techniques in Neural Networks Video
10. Hands-on on MLP for classification problem Video

Week 3 Convolutional Neural Networks

11. Fundamentals of Image representation and Image preprocessing and Data augmentation Video
12. Introduction to Convolutional Neural Networks, Inspiration behind CNN, Key Components of CNN Video
13. Convolution for RGB, Pooling Layer and Flatten Layer Video
14. Batch Normalization Video
15. Hands-on session on building simple CNN model Video

Week 4 Varients of CNN Architectures

16. Architecture and Implementation of AlexNet Video
17. VGGNet (VGG16 and VGG19) and GoogleNet Video
18. Introduction to ResNet (ResNet 34 and ResNet50) Video
19. Introduction to Transfer Learning Video
20. Hands-on on standard CNN architectures and transfer learning Video
21. Hands-on on building and deep CNN ensemble model. Video

Week 5 Explainable AI: Concepts and Techniques

22. Need for XAI, PCI, Occlusion method Video
23. SHAP and LIME Video
24. Guided backpropagation Video
25. Grad-CAM and Class Activation Maps (CAMs) Video
26. Hands-on implemenation of XAI methods Video

Week 6 CNN based Segmentation & Object Detection Algorithms

27. Image segmentation Video
28. U-Net with Attention and Evaluation Metric for Segmentation Video
29. Object detection Video
30. YOLO v1 for object detection Video
31. Hands-on implemenation of Unet Video
32. Creating .yaml file for the custom dataset Video
33. Hands-on implemenation of YOLO Video

Week 7 Sequence-to-Sequence models (Recurrent Neural Netorks)

34. Introduction to Recurrent Neural Networks Video
35. Numerical Example for RNN Video
36. Vanishing and exploding gradients in NN Video
37. Backpropagation through time (BTT) Video
38. Hands-on implementation of RNN model and its variants. Video

Week 8 Long-short term memory (LSTM)

39. Introduction to LSTM Video
40. Gated Recurrent Unit Video
41. LSTM-Encoder Decoder Structure Video
42. LSTM with attention Video
43. Hands-on implementation of LSTM Video

Week 9 Natural Language Processing

44. Introduction to NLP Video
45. Text Preprocessing and Text Representations Video
46. Discrete and Distributed Word Representation Video
47. Word Embeddings in NLP Video
48. Hands-on implementation of RNN in NLP application Video

Week 10 Autoencoders (AEs) and Variational Autoencoders (VAEs)

49. Introduction to Autoencoders Video
50. Types of Autoencoders Video
51. VAE Architecture - Encoder part Video
52. VAE Architecture - Decoder part Video
53. Reparameterization Trick Video
54. Hands-on implemenation of Autoencoders Video

Week 11 Large Language Models (LLMs)

55. Foundations of Language Modeling and Transformers Video
56. Transformer Architectures and Attention Mechanisms Video
57. In-context learning and Self-Supervised Learning in LLMs Video
58. Large Language Models: Tokenization, Generation, and Sampling Video
59. Pre-training and Instruction Tuning of Large Language Models Video
60. Reinforcement Learning for Aligning Large Language Models Video

Week 12 Large Language Models (continued) and Diffusion Models

61. Reasoning, Retrieval, and Efficiency in Post-trained LLMs Video
62. Evaluation, Benchmarking, and Impact of Foundation Models Video
63. LLMs demo -TA Video
64. Diffusion Models for Generative Modelling Video
65. GANs and Diffusion models demo -TA Video