M.Tech. VLSI Design & CAD:Neural Networks
Master
In Patiala
Description
-
Type
Master
-
Location
Patiala
Facilities
Location
Start date
Start date
Reviews
Course programme
First Semester I
Physics of Semiconductor Devices
IC Fabrication Technology
Digital VLSI Design
CAD Systems Environment
Research Methodology
Second Semester
Analog IC Design
Hardware Description Languages
Embedded Systems
Third Semester
Seminar
Thesis starts
Fourth Semester
Thesis
Neural Networks
Introduction and Motivation: Biological Neural networks and simple models, The Artificial Neuron model, Why Artificial Networks, Characteristics of Neural Networks, Historical perspectives.
Fundamentals of Neural Networks: The biological prototype, neuron, synapses and dendrites. Single and Multi layer neural networks. their variants and Applications Terminology, notations and representation of Neural Networks. Training of Neural Networks.
Supervised and Unsupervised Learning, categorization using ANNs.
Perceptrons: History, Representation of perceptrons and issues, perceptron learning and training.
Back propagation: Concept, Back propagation training algorithm, Applications of Back propagation.
Counter propagation networks: Introduction and structure, Layers and their training, Application of counter propagation.
Hopfield nets: Energy functions and Optimization Bi-directional Associative memories, Optical neural networks, The cognitron and Neocognitron, structure and training.
Competitive Learning, Feature Mapping, Self Organizing Maps.
Adaptive Resonance Theory: Stability ?V Plasticity dilemma, ART1 & ART2.
Hardware realization of ANNs.
Recent trends and Future Directions.
M.Tech. VLSI Design & CAD:Neural Networks