IISc Bangalore RV University · Computer Science

Foundations of Deep Learning: Concepts and Applications

Prof. Ashwini Kodipalli, Prof. Baishali Garai, Prof. Sriram Ganapathy · 65 free video lectures

65 video lectures. Topics: Overview of Machine Learning and Deep Learning; Single Layer Perceptron; Hands-on on Single Layer Perceptron; Multi-Layer Perceptron; Activation and Loss Functions; Gradient descent algorithm; Backpropagation in Neural Network; Varients of Gradient descent and Momentum…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Overview of Machine Learning and Deep Learning
  2. Single Layer Perceptron
  3. Hands-on on Single Layer Perceptron
  4. Multi-Layer Perceptron
  5. Activation and Loss Functions
  6. Gradient descent algorithm
  7. Backpropagation in Neural Network
  8. Varients of Gradient descent and Momentum based techniques
  9. Regularization techniques in Neural Networks
  10. Hands-on on MLP for classification problem
  11. Fundamentals of Image representation and Image preprocessing and Data augmentation
  12. Introduction to Convolutional Neural Networks, Inspiration behind CNN, Key Components of CNN
  13. Convolution for RGB, Pooling Layer and Flatten Layer
  14. Batch Normalization
  15. Hands-on session on building simple CNN model
  16. Architecture and Implementation of AlexNet
  17. VGGNet (VGG16 and VGG19) and GoogleNet
  18. Introduction to ResNet (ResNet 34 and ResNet50)
  19. Introduction to Transfer Learning
  20. Hands-on on standard CNN architectures and transfer learning
  21. Hands-on on building and deep CNN ensemble model.
  22. Need for XAI, PCI, Occlusion method
  23. SHAP and LIME
  24. Guided backpropagation
  25. Grad-CAM and Class Activation Maps (CAMs)
  26. Hands-on implemenation of XAI methods
  27. Image segmentation
  28. U-Net with Attention and Evaluation Metric for Segmentation
  29. Object detection
  30. YOLO v1 for object detection
  31. Hands-on implemenation of Unet
  32. Creating .yaml file for the custom dataset
  33. Hands-on implemenation of YOLO
  34. Introduction to Recurrent Neural Networks
  35. Numerical Example for RNN
  36. Vanishing and exploding gradients in NN
  37. Backpropagation through time (BTT)
  38. Hands-on implementation of RNN model and its variants.
  39. Introduction to LSTM
  40. Gated Recurrent Unit
  41. LSTM-Encoder Decoder Structure
  42. LSTM with attention
  43. Hands-on implementation of LSTM
  44. Introduction to NLP
  45. Text Preprocessing and Text Representations
  46. Discrete and Distributed Word Representation
  47. Word Embeddings in NLP
  48. Hands-on implementation of RNN in NLP application
  49. Introduction to Autoencoders
  50. Types of Autoencoders
  51. VAE Architecture - Encoder part
  52. VAE Architecture - Decoder part
  53. Reparameterization Trick
  54. Hands-on implemenation of Autoencoders
  55. Foundations of Language Modeling and Transformers
  56. Transformer Architectures and Attention Mechanisms
  57. In-context learning and Self-Supervised Learning in LLMs
  58. Large Language Models: Tokenization, Generation, and Sampling
  59. Pre-training and Instruction Tuning of Large Language Models
  60. Reinforcement Learning for Aligning Large Language Models
  61. Reasoning, Retrieval, and Efficiency in Post-trained LLMs
  62. Evaluation, Benchmarking, and Impact of Foundation Models
  63. LLMs demo -TA
  64. Diffusion Models for Generative Modelling
  65. GANs and Diffusion models demo -TA

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IISc Bangalore RV University.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights