KBCNMU TY AI & DS syllabus

KBCNMU · Third Year B.E. Artificial Intelligence & Data Science · NEP 2020

Deep Learning and Neural Network

AIDS-606 B · Elective III · Semester VI · 3 credits · ISE 40 + ESE 60

One of the Elective III options.

  1. Unit 1: Introduction

    9 hours

    Neural networks and the brain, models of a neuron, networks as directed graphs, feedback and architectures; Rosenblatt's perceptron, its convergence theorem and its relation to the Bayes classifier.

    Examined in the 60-mark end-semester paper

    • Biological and artificial neurons
    • Feed-forward network architectures
    • Perceptron learning rule
  2. Unit 2: Supervised and Unsupervised Neural Networks

    9 hours

    Architecture and training of Hebb, perceptron, back-propagation, associative-memory, Hopfield, counter-propagation and adaptive resonance theory networks.

    Examined in the 60-mark end-semester paper

    • Hebbian, perceptron and delta learning rules
    • Multilayer perceptron and backpropagation
    • Hopfield networks and bidirectional associative memory
    • Counter-propagation networks
    • Adaptive resonance theory: ART1 and ART2
  3. Unit 3: Advanced Neural Networks

    9 hours

    Kohonen self-organising feature maps, learning vector quantisation, the Boltzmann machine, the cognitron and neocognitron, and optical neural networks with electro-optical multipliers and holographic correlators.

    Examined in the 60-mark end-semester paper

    • Kohonen self-organising maps
    • Learning vector quantisation
    • Boltzmann machines and deep belief networks
    • Cognitron and neocognitron
  4. Unit 4: Deep Learning

    9 hours

    Machine-learning basics and linear regression, under- and over-fitting, support vector machines, deep feed-forward, convolutional and recurrent networks, deep Boltzmann machines, and applications in speech and language.

    Examined in the 60-mark end-semester paper

    • Bias-variance trade-off
    • Support vector machines
    • Convolution and feature maps
    • Recurrent neural networks
  5. Unit 5: GANs and Training Deep Networks

    9 hours

    Encoder–decoder and generator–discriminator architectures; challenges in training — data augmentation and hyperparameters; transfer learning; developing and deploying models with TensorFlow or PyTorch.

    Examined in the 60-mark end-semester paper

    • Generative adversarial networks
    • Data augmentation
    • Transfer learning
    • Deploying deep learning models

Unit contents are summarised from the official KBCNMU syllabus . AiCanCode.org is not affiliated with Kavayitri Bahinabai Chaudhari North Maharashtra University (KBCNMU).