| Course Code: CS401M Course Name: Machine Intelligence Prerequisites: Nil Syllabus: Pre-requisites: NIL Mathematical foundations: Preliminary concepts of Linear Algebra and Statistics; Introduction to Machine Learning, Supervised Learning: Linear regression, logistic regression, support vector machine, neural network; Bayesian Learning; Bias, Variance trade-off: Overfitting and Under-fitting; Unsupervised Learning: Clustering, Density Estimation, DB Scan; Dimension reduction: Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA); Deep Learning: Motivation of Deep Learning, Convolution Neural Network (CNN): Basic architecture and different models (AlexNet, VGG, Google Net, ResNet etc.), Sequential Learning: Recurrent Neural Network (RNN), Gated RNN, Long Short-Term Memory; Generative Adversarial Network (GAN), Transformers, Large Language Models (LLM), Concept of Reinforcement Learning, Deep-RL: Deep Q-Learning. Textbook: 1. O. Duda, P. E. Hart, D. Strok, Pattern classification, 2nd edition, Wiley, 2000. 2. Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016,br> 3. Understanding Deep Learning by Simon J D Prince. References: 1. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011. 2. Tom M Mitchell, Machine Learning, McGraw-Hill 3. Eli Stevens, Luca Antiga, Thomas Viehmann, Deep Learning with PyTorch: Build, train, and tune neural networks using Python tools, First Edition, Manning, 2020. |