Artificial Neural Networks Detailed Syllabus for B.Tech third year second sem is covered here. This gives the details about credits, number of hours and other details along with reference books for the course.<\/p>\n
The detailed syllabus for Artificial Neural Networks B.Tech 2016-2017 (R16) third year second sem is as follows.<\/p>\n
B.Tech. III Year II Sem. \u00a0 L\/T\/P\/C
\nCourse Code:MT622OE \u00a0 \u00a03\/0\/0\/3<\/p>\n
Course Objectives:<\/strong><\/p>\n Course Outcomes:<\/strong> By completing this course the student will be able to:<\/p>\n UNIT – I \u00a0Introduction:<\/strong> A Neural Network, Human Brain, Models of a Neuron, Neural Networks\u00a0viewed as Directed Graphs, Network Architectures, Knowledge Representation, Artificial\u00a0Intelligence and Neural Networks\u00a0Learning Process: Error Correction Learning, Memory Based Learning, Hebbian Learning,\u00a0Competitive, Boltzmann Learning, Credit Assignment Problem, Memory, Adaption,\u00a0Statistical Nature of the Learning Process<\/p>\n UNIT – II\u00a0Single Layer Perceptron:<\/strong> Adaptive Filtering Problem, Unconstrained Organization\u00a0Techniques, Linear Least Square Filters, Least Mean Square Algorithm, Learning Curves,\u00a0Learning Rate Annealing Techniques, Perceptron \u2013Convergence Theorem, Relation Between\u00a0Perceptron and Bayes Classifier for a Gaussian Environment\u00a0Multilayer Perceptron: Back Propagation Algorithm XOR Problem, Heuristics, Output\u00a0Representation and Decision Rule, Computer Experiment, Feature Detection<\/p>\n UNIT – III\u00a0Back Propagation:<\/strong> Back Propagation and Differentiation, Hessian Matrix, Generalization,\u00a0Cross Validation, Network Pruning Techniques, Virtues, and Limitations of Back\u00a0Propagation Learning, Accelerated Convergence, Supervised Learning<\/p>\n\n
\n