BCSE332L - Deep Learning

Instructor
Dr. Bhargavi R
Venue
Slot E1 & TE1 - AB3 Block 404

Course Overview

This course provides an introduction to the fundamental concepts and applications of deep learning, a subfield of machine learning that focuses on neural networks. The course starts with basic Feed-forward Neural Networks and then moves ahead with how to improve the performance by going deeper with more layers and playing with other hyper parameters. Differnt types of Deep Neural Networks to handle different types of data like CNN for handling images, RNN for NLP are also covered in this course. Students will gain a comprehensive understanding of the theoretical foundations and practical implementation of deep learning algorithms. More details on the topics covered can be obtained from the syllabus

Syllabus

You can find the syllabus of this course here

Prerequisites

Prior knowledge of the following subjects help you to understand appreciate the Deep Learning Course better

Textbooks

Following are the text books for reference -

Tentative Schedule

Date Lecture Readings Announcements
Welcome to Deep Learning!
Thu, 4th Jan Lecture 1: Meet and Greet, Introduction to Deep Learning [Slides ]
  • Ch 1 - Ian Goodfellow

Model Question Paper
Fri, 5th Jan Lecture 2: ML paradigms,Loss functions, Model eavaluation [Slides ]
  • Ch1, Ch5 - ISLR
Tue, 9th Jan Lecture 3: Model Validation, History of ANN, MLP [Slides ]
  • Ch 1 - Ian Goodfellow
Thu, 11th Jan Lecture 4: Perceptron [Slides ] [Lecture ]
  • Ch 1 - Michael Nielsen

Homework Release
Fri, 12th Jan Lecture 5: Gradient descent [Slides ]
  • Ch 4 - Ian Goodfellow
Thu, 18th Jan Lecture 6: Gradient discent, Learning in MLP [Slides ]
  • Ch 1 - Ian Goodfellow
  • Ch 2 - Michael Nielsen
Fri, 19th Jan Lecture 7: Backpropagation [Slides ]
  • Ch 1 - Ian Goodfellow
  • Ch 2 - Michael Nielsen
Sat, 20th Jan Lecture 8: Activation functions [Slides ]
  • Ch 6 - Ian Goodfellow
Tue, 23 Jan Lecture 9: Parameters & Hyperparameters, Bias & Variance [Slides ]
  • Ch 7 - Ian Goodfellow
Tue, 30 Jan Lecture 10: Regularization, Ensenbled models, L1, L2, Dropout [Slides ]
  • Ch 7 - Ian Goodfellow
Thu, 01 Feb Lecture 11: Early stopping, BatchNorm, SGD with momentum [Slides ]
  • Ch 7 - Ian Goodfellow
  • Ch 8 - Ian Goodfellow
Fri, 02 Feb Lecture 12: NAG with momentum, AdaGrad [Slides ]
  • Ch 8 - Ian Goodfellow
Tue, 06 Feb Lecture 13: RMSProp, AdaDelta, Adam [Slides ]
  • Ch 8 - Ian Goodfellow
Tue, 20 Feb Lecture 14: Introduction to computer vision, CNN [Slides ]
  • Ch 9 - Ian Goodfellow
Thu, 22 Feb Lecture 15: CNN architecture, Convolution Operations [Slides ]
  • Ch 9 - Ian Goodfellow
Thu, 23 Feb Lecture 16: Pooling, Stride, Padding [Slides ]
  • Ch 9 - Ian Goodfellow
Fri, 23 Feb Lecture 17: Transfer Learning, LeNet, AlexNet [Slides ] [Transfer learning slides ] [AlexNetPaper ]
  • Research Papers
Tue, 27 Feb Lecture 18: VGGNet [Slides ] [VGGNetPaper ]
  • Research Paper
Thu, 29 Feb Lecture 19: ResNet [Slides ] [ResNetPaper ]
  • Research Paper
Fri, 01 Mar Lecture 20: Inception/GoogleNet, Parameter computation problems [Slides ] [GoogleNetPaper ]
  • Research Paper
Tue, 05 Mar Lecture 21: Object Detection introduction to basic concepts, Object localization, Sliding window algorithm [Slides ] [D2L Chapter 14 ]
Tue, 12 Mar Lecture 22: IoU, NMS, Introducto RCNN [Slides ] [RCNN Paper ] [DNN for Vision Chapter ]
  • Research Paper
Thu, 14 Mar Lecture 23: RCNN [Slides ]
Fri, 15 Mar Lecture 24: Fast RCNN, FC to CNN [Slides ] [Fast RCNN Paper ] [DNN for Vision Chapter ]
  • Fast RCNN Research Paper
Tue, 19 Mar Lecture 25: YOLO [Slides ] [YOLO Paper ] [DNN for Vision Chapter ]
  • YOLO Research Paper
Thu, 21 Mar Lecture 26: Autoencoder [Slides ]
  • Ch 14 - Ian Goodfellow
Fri, 22 Mar Lecture 27 Autoencoder, VAE, introduction to GAN [Slides ]
  • Ch 14 - Ian Goodfellow
Tue, 26 Mar Lecture 28: GAN [Slides ] [GAN Paper ] [DNN for Vision Chapter ]
  • Ch 20 - Ian Goodfellow
  • GAN Research Paper
Thu, 28 Mar Lecture 29: GAN, Problems discussion [Slides ] [D2L Chapter 20 ]
  • Ch 20 - Ian Goodfellow
Fri, 12 April Lecture 30: Introduction to Sequence structures, RNN [Slides ] [D2L Chapter 20 ]
  • Ch 10 - Ian Goodfellow
  • Ch 9 - D2L
Tue, 16 April Lecture 31: BPTT, Bidirectional RNN [Slides ]
  • Ch 10 - Ian Goodfellow
  • Ch p - D2L
Thu, 18 April Lecture 32: Deep RNN, Vanishing and exploding gradients, Encoder Decoder, Sequnce-to-sequence architectures [Slides ]
  • Ch 10 - Ian Goodfellow
  • Ch 9 - D2L
Tue, 23 April Lecture 33: Encoder Decoder, Sequnce-to-sequence architectures [Slides ]
  • Ch 10 - Ian Goodfellow
  • Ch 9- D2L
Thu, 25 April Lecture 34: LSTM, GRU [Slides ]
  • Ch 10 - Ian Goodfellow
  • Ch 10 - D2L
Fri, 26 April Lecture 35: Introduction to Reinforcement Learning, Q learning [Slides ] [RL book Chapters ]
Tue, 30 April Lecture 36: DQN [Slides ] [RL book Chapters ]
Thu, 02 May Lecture 37: Policy Gradients, Actor-Critic model [Slides ] [RL book Chapters ]
Fri, 03 May Lecture 38: Revision
Course Completed. All the Best!