AI-Powered Learning Platform

Subject Syllabus

CSIT-602 - Machine Learning

CSIT · Semester 6

Course Modules

Learn topic-wise with Hyper AI and revise using mapped PYQs.

Introduction to machine learning, scope and limitations Regression Probability, statistics and linear algebra for machine learning Convex optimization Data visualization Hypothesis function and testing Data distributions Data preprocessing and data augmentation Normalizing data sets Machine learning models Supervised and unsupervised learning

Linearity vs non-linearity Activation functions like sigmoid and ReLU Weights and bias Loss function Gradient descent Multilayer network Back propagation Weight initialization Training and testing Unstable gradient problem Auto encoders Batch normalization Dropout L1 and L2 regularization Momentum Tuning hyper parameters

Convolution neural network Flattening, sub sampling, padding and stride Convolution layer, pooling layer and loss layer Dense layer and 1x1 convolution Inception network Input channels Transfer learning One shot learning Dimension reductions Implementation of CNN using frameworks like TensorFlow and Keras

Recurrent neural network Long short-term memory Gated recurrent unit Translation Beam search and width BLEU score Attention model Reinforcement learning and RL-framework MDP Bellman equations Value iteration and policy iteration Actor-critic model Q learning SARSA

Support Vector Machines Bayesian learning Application of machine learning in computer vision Speech processing Natural language processing Case study: ImageNet Competition