BAIC — Calicut University B.C.A Honours Programme Scheme and Syllabus | BAIC

Detailed Syllabus Page 156 of 241 Module Unit Content Hrs (48+12) Marks I Neural Networks and Deep Learning 10 15 1 Introduction to neural networks -Single layer perceptrons, Multi- Layer Perceptrons (MLPs) 1 2 Representation Power of MLPs, Activation functions - Sigmoid, Tanh, ReLU, Softmax 3 3 Risk minimization, Loss function, Training MLPs with backpropagation 3 4 The Problem of Overfitting, Vanishing and exploding gradient problems 3 II Deep Learning and optimization technique 12 15 5 Introduction to deep learning, Deep feed forward network 3 6 Training deep models. Eigen value, Eigen vector concepts.

3 7 Optimization techniques - Gradient Descent (GD), GD with momentum, Nesterov accelerated GD, Stochastic GD 2 8 Regularization Techniques - L1 and L2 regularization, Early stopping 2 9 Dataset augmentation, Parameter sharing and tying, Injecting noise at input, Ensemble methods. 2 III Convolution Neural Networks 13 20 10 Convolution operation, Motivation 1 11 Pooling, Convolution and Pooling as an infinitely strong prior 3 12 Variants of convolution functions 2 13 Structured outputs 2 14 Data types 1 15 Efficient convolution algorithms 3