BAMU · Third Year B.E./B.Tech Computer Science and Engineering · NEP 2020
Artificial Neural Network
PCCT-1 · Semester VI · 3 credits · CIA 40 + SEE 60
As printed, Module II repeats Module I's text under the heading Associative Learning.
Module 1: Characteristics of Neural Networks; Perceptron Learning
15 hoursBiological and artificial neural networks, MP, perceptron and Adaline neuron models, topology, basic learning laws, supervised and unsupervised learning and the functional units for pattern recognition; single- and multilayer perceptrons, linear and non-linear separability, error-correction and gradient-descent rules, feed-forward networks and backpropagation for pattern classification and association.
Examined in the 60-mark end-semester paper
- Artificial neuron models
- Neural network architectures
- Basic learning laws
- Perceptron learning rule
- Backpropagation training
Module 2: Associative Learning
15 hoursAs printed, this module repeats Module I's text (neuron models, learning laws, perceptron and feed-forward learning) under the heading Associative Learning, and adds the basic functional units of ANN for pattern association, classification and mapping.
Examined in the 60-mark end-semester paper
- Associative memory
- Pattern association, classification and mapping
Module 3: Competitive Learning; Self-Organizing Maps
15 hoursComponents of a competitive-learning network, pattern clustering and feature-mapping networks, ART networks and character recognition with ART; feature-mapping models, the SOM algorithm and properties of feature maps, learning vector quantisation and adaptive pattern classification.
Examined in the 60-mark end-semester paper
- Competitive learning and ART networks
- Self-organising maps
- Learning vector quantisation
Module contents are summarised from the official BAMU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Marathwada University (BAMU).