22CST101: Neural Networks

This course offers an in-depth introduction to the fundamentals and advanced concepts of neural networks. It covers key topics such as perceptrons, feedforward networks, backpropagation, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and deep learning architectures. Students will learn about network training, optimization techniques, and the practical implementation of neural networks using popular frameworks like TensorFlow and PyTorch. The course includes hands-on projects to apply theoretical knowledge to real-world problems in image recognition, natural language processing, and other AI applications. Ideal for students and professionals aiming to excel in artificial intelligence and machine learning.

Course Instructor:

sometext

Sadbhawna

Contact: sadbhawnathakur [at] gmail [dot] com

profile photo

Textbooks:


Lectures:

Wednesday Thursday Friday
Week 1 24/07     25/07     26/07 1. Why Neural Networks    
Week 2 31/08 2. Introduction to Neural Networks    01/08 3. Linear Regression    02/08 4. Gradient Descent Algorithm   
Week 3 07/08 5. Logistic Regression    08/09 6. Optimization in Logistic Regression    09/08 7. Multi-class Logistic Regression    
Week 4 14/08 8. Optimizing categorical_cross-entropy loss     15/08 ***Holiday***     16/08 9_Why Multi-layer Neural Network    
Week 5 21/08 10. Activation Functions     22/08 11. Backpropagation in neural networks     23/08 12. Backpropagation-2    
Week 6 28/08 13.Backpropagation-3     29/08 14. Optimization in NN     30/08 15. Regularization in NN    
Week 7 04/09 16.Preprocessing in NN     05/09 17. Introduction to RNNs-1     06/09 18. Introduction to RNNs-2    
Week 8 11/09 19. LSTMs in RNN     12/09 20. Variations in LSTM     13/09 21. Encoder-decoder    
Week 9 18/09 22. Convolutions_1         19/09 23. Convolution_2         20/09 24. CNN Properties        
Week 10 25/09 ***Mid-sem Exams***     26/09 ***Mid-sem Exams***     27/09 ***Mid-sem Exams***    
Week 11 02/10 ***Holiday***     03/10 25. CNN Properties 2         04/10 26. Backpropagation in CNN 1        
Week 12 09/10 27. Backpropagation in CNN 2     10/10 28. Backpropagation in CNN 3     11/10 ***Holiday***    
Week 13 16/10 29. CNN Architectures 1     17/10 30. CNN Architectures 2     18/10 31. CNN Architectures 3    
Week 14 23/10 32. Variational Auto-encoders 1     24/10 33. Variational Auto-encoders 2     25/10 34. Variational Auto-encoders 3    
Week 15 30/10 ***Mid-sem break***    31/10 ***Mid-sem break***    01/11 ***Mid-sem break***   
Week 16 06/11 35. Generative Adversarial Netwoorks-1     07/11 36. Generative Adversarial Netwoorks-2     08/11 37. Generative Adversarial Netwoorks-3    
Week 17 13/11 38. Pix 2 pix GAN     14/11 39. Cycle GAN     15/11 40. Quiz    


Last updated on July 22, 2024