BAMU · Third Year B.E./B.Tech Information Technology · NEP 2020
Artificial Neural Network
PCCT-1 · Semester VI · 3 credits · CIA 40 + SEE 60
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 functional units for pattern recognition; single- and multilayer perceptrons, linear separability, error-correction and gradient-descent rules, feedforward networks and backpropagation.
Examined in the 60-mark end-semester paper
- Artificial neuron model
- McCulloch–Pitts neuron and logic functions
- Perceptron, Adaline and Madaline
- Learning rules: Hebbian and delta
- Backpropagation networks
Module 2: Associative Learning
15 hoursPattern association, classification and mapping tasks; associative learning, Hopfield networks and their error performance, simulated annealing, the Boltzmann machine and Boltzmann learning, state-transition diagrams, false minima and stochastic update.
Examined in the 60-mark end-semester paper
- Pattern association, classification and mapping tasks
- Associative memory
- Hopfield networks
- Simulated annealing and tabu search
- Boltzmann machine and Boltzmann learning
Module 3: Competitive Learning and ART; Self-Organising Maps
15 hoursComponents of competitive-learning networks, pattern clustering and feature mapping, ART networks and character recognition with ART; feature-mapping models, the SOM algorithm and its properties, learning vector quantisation and adaptive pattern classification.
Examined in the 60-mark end-semester paper
- Competitive learning networks and feature mapping
- ART networks
- Kohonen self-organising maps
- Learning vector quantization
Module contents are summarised from the official BAMU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Marathwada University (BAMU).