Deep Learning Course by Dr. Rupam Bhattacharya @ IIIT Bhagalpur

Deep Learning using Pytorch.

Content:

Lecture 1:
● Brief overview of Pytorch.
● Popular Deep Learning Frameworks.
● Installing Pytorch in your machine.
● Introduction to Google Colab.
● Getting started with Google Colab.
Lecture 2:
Pytorch Basics.
– Tensor
● Example
● Numeric type
● Operations
● NumPy bridge
Lecture 3:
● Representing data through Pytorch Tensor
● Introduction
● Working with image
Lecture 4:
● Representing tabular data
● Working with time series
Lecture 5:
● Representing text
Lecture 6:
● Mechanics of Learning-PART I
● Introduction
● Example
– Application of Linear Model
Lecture 7:
● Mechanics of Learning-PART II
● Pytorch’s autograd
Lecture 8:
● Mechanics of Learning-PART III
● Optimizers
Lecture 9:
● Mechanics of Learning-PART IV
● Training, validation, and overfitting
Lecture 10:
● Mechanics of Learning-PART V
● Artificial Neural Network
Lecture 11:
● Mechanics of Learning-PART VI
● PyTorch nn module
Lecture 12:
Mechanics of Learning-PART VI continued...
Lecture 13:
● Module 2
● Understanding Convolutions
Lecture 14:
● Brief discussion on Convolution through PyTorch
Lecture 15:
● More on Convolution
Lecture 16:
● Discussion on ConvNet
Lecture 17:
● Discussion on building a simple ConvNet using PyTorch
Lecture 18:
● Discussion on building a simple ConvNet using PyTorch
Lecture 19:
● Examples related to Classic Networks in Computer Vision
Lecture 20:
● Examples related to Classic Networks in Computer Vision
● Building Very Deep Models in Pytorch
Lecture 21:
● Module 3
– Introduction to Recurrent Neural Network (RNN)
Lecture 22:
● RNN continued..
Lecture 23:
– Backpropagation through time
– Example (RNN using PyTorch)
Lecture 24:
– Problems with RNN
– Gated Recurrent Unit
Lecture 25:
● Long Short Term Memory networks (LSTMs)
● Bidirectional RNN
Lecture 26:
● Introduction to Generative Adversarial Networks (GANs)
Lecture 27:
● GANs continued
Lecture 28:
● Generative Adversarial Networks (GANs)
Lecture 29:
● GANs in PyTorch

References

All the contents present in the slides were taken from various online resources.
These slides are used for academic purposes only.

Class 1: https://pytorch.org/ , https://developer.nvidia.com/cuda-toolkit
Class 2 to Class 12: Slide credit: E. STEVENS, L. ANTIGA, and T. VIEHMANN
Class 13: Slide Credit: Prof. Andrew Ng; E. STEVENS, L. ANTIGA, and T. VIEHMANN
Class 14: Slide Credit: https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html ; Prof. Andrew Ng; E. STEVENS, L. ANTIGA, and T. VIEHMANN
Class 15: Slide Credit: Prof. Andrew Ng;
Class 16: Slide Credit: Prof. Andrew Ng;
Class 17: Slide Credit: E. STEVENS, L. ANTIGA, and T. VIEHMANN
Class 18: Slide Credit: E. STEVENS, L. ANTIGA, and T. VIEHMANN
Class 19: [1] LeCun, Yann, et al. "Gradient-based learning applied to document recognition." Proceedings of the IEEE 86.11 (1998): 2278-2324. [2] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012. [3] Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). [4] He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Class 20: [4] He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Class 21 and 22: Prof. Andrew Ng
Class 23: F. Li & J. Johnson & S. Yeung; Prof. Andrew Ng;
Class 24: A. Zhang, Z. C. Lipton, M. Li, and A. Smola, Prof. Andrew Ng;
Class 25: Christopher Olah, Prof. Andrew Ng;
Class 26: : A. Zhang, Z. C. Lipton, M. Li, and A. Smola;
Class 27,28: Dr. G. Krishnamurthy;
CLass 29 : A. Persson;