-
Introduction to Artificial Neural Networks: Elementary
Neurophysiology, Neural Circuits for computation and Hibbing learning.
Artificial neurons as processing elements, perception. Neural Network
simulation and data structures.
-
Back Propagation: Back propagation network (BPN) approach
and operation. Generalized data rule-updates of output layer weights and
hidden layer weights,. BPN implementation issue. Training data, network
sizing, weights and learning parameters. BP Applications – Data
compression and paint quality inspection. Back propagation simulation for
signal propagation-BPN data structure, signal propagation algorithms and
error-propagation.
-
Neural Network Memories: Introduction to Associative memory
–Hamming distance, linear associate, Bi- directional Associative memory
(BAM) Architecture, Processing, Mathematics and Energy Function. Hopfield
memory – Discrete Hopfield Memory. Continuous Hopfield Model Traveling
– sales person problem. BAM simulation – Bidirectional connections,
data structures initialization algorithms and signal propagation.
-
Simulated Annealing: Information theory and statistical
mechanic concepts, Real and Simulated Annealing. Boltzman machine-Basic,
Architecture and processing, learning in Boltzman simulator-Modified.
Boltzman Networks its data structure and algoritm.
-
Counter Propagation Networks (CPN) : Counter propagator
Network building Blocks- Input Layer, Instar, competitive Networks and
outstare CPN data processing – Forward mapping, Training CPN and its
completed implementation the CPN simulator –Data structure, Algorithms
and completed simulator.
-
Self-Organizing Maps (SOM): SOM Data processing, data
structure and learning algorithms.
1
James A Freeman – Neural Networks Algorithms Applications an
Programming Techniques, Pearson Education Asia.
2
Simon Haykin – Neural Networks 2/e, Pearson Education Asia.
3
Yagya Narayan – Artificial Neural Networks, Prentice Hall India,
1999. |