Syllabus Artificial Neural Network - (317531) Credit Examination Scheme : 03 Mid_Semester (TH) : 30 Marks End_Semester (TH) : 70 Marks Unit I Introduction to ANN Introduction to ANN, History of Neural Network, Structure and working of Biological Neural Network, Neural net architecture, Topology of neural network architecture, Features, Characteristics, Types, Activation functions, Models of neuron-Mc Culloch & Pitts model, Perceptron, Adaline model, Basic learning laws, Applications of neural networks, Comparison of BNN and ANN. (Chapter - 1) Unit II Learning Algorithms Learning and Memory, Learning Algorithms, Numbers of hidden nodes, Error Correction and Gradient Decent Rules, Perceptron Learning Algorithms, Supervised Learning Backpropagation, Multilayered Network Architectures, Back propagation Learning Algorithm, Feed forward and feedback neural networks, example and applications. (Chapter - 2) Unit III Associative Learning Introduction, Associative Learning, Hopfield network, Error Performance in Hopfield networks, simulated annealing, Boltzmann machine and Boltzmann learning, State transition diagram and false minima problem, stochastic update, simulated annealing. Basic functional units of ANN for pattern recognition tasks : Pattern association, pattern classification and pattern mapping tasks. (Chapter - 3) Unit IV Competitive learning Neural Network Components of CL network, Pattern clustering and feature mapping network, ART networks, Features of ART models, character recognition using ART network. Self-Organization Maps (SOM) : Two Basic Feature Mapping Models, Self-Organization Map, SOM Algorithm, Properties of Feature Map, Computer Simulations, Learning Vector Quantization, Adaptive Pattern Classification. (Chapter - 4) Unit V Convolution Neural Network Building blocks of CNNs, Architectures, convolution / pooling layers, Padding, Strided convolutions, Convolutions over volumes, SoftMax regression, Deep Learning frameworks, Training and testing on different distributions, Bias and Variance with mismatched data distributions, Transfer learning, multi-task learning, end-to-end deep learning, Introduction to CNN models : LeNet - 5, AlexNet, VGG - 16, Residual Networks. (Chapter - 5) Unit VI Applications of ANN Pattern classification - Recognition of Olympic games symbols, Recognition of printed Characters. Neocognitron - Recognition of handwritten characters. NET Talk : to convert English text to speech. Recognition of consonant vowel (CV) segments, texture classification and segmentation. (Chapter - 6)
