Module 1
Introduction – Principles – artificial neuron – activation functions – Single layer & multi-layer networks – Training artificial neural networks – Perception – Representation – Linear separability – Learning – Training algorithms.
Introduction – Principles – artificial neuron – activation functions – Single layer & multi-layer networks – Training artificial neural networks – Perception – Representation – Linear separability – Learning – Training algorithms.
Module 2
Back Propagation – Training algorithm – Applications – network configurations – Network paralysis – Local minima – temporal instability.
Back Propagation – Training algorithm – Applications – network configurations – Network paralysis – Local minima – temporal instability.
Module 3
Counter Propagation networks Kebenon layer – Training the cohenen layer – Pre initializing the wright vectors – statistical properties – Training the Grosbery layer – Full counter propagation network – Application.
Counter Propagation networks Kebenon layer – Training the cohenen layer – Pre initializing the wright vectors – statistical properties – Training the Grosbery layer – Full counter propagation network – Application.
Module 4
Statistical methods- Boltzmann’s Training – Cauche training – Artificial specific heat methods – Applications to general non-linear optimization problems.
Module 5
Hopfield nets – Recurrent networks – stability – Associative memory – applications – Thermo dynamic systems – Statistical Hopfield networks – Bi-directional associative memories – Continuous BAM – Adaptive resonance theory – Architecture classification – Implementation.
Statistical methods- Boltzmann’s Training – Cauche training – Artificial specific heat methods – Applications to general non-linear optimization problems.
Module 5
Hopfield nets – Recurrent networks – stability – Associative memory – applications – Thermo dynamic systems – Statistical Hopfield networks – Bi-directional associative memories – Continuous BAM – Adaptive resonance theory – Architecture classification – Implementation.
Text Book
Neural Computing Theory & Practice – Philip D. Wasserman.
mgu university b.tech syllabus electronics
References
1. Neural Networks – Simon Haykins, Pearson Education.
2. Adaptive Pattern Recognition & Neural Networks – Pay Y.H.
3. An Introduction to neural computing – Chapman & Hall
4. Artificial Neural Networks – Robert J. Schalkoff, McGraw Hill
5. Artificial Neural Networks – B.Yegnanarayana, PHI
2. Adaptive Pattern Recognition & Neural Networks – Pay Y.H.
3. An Introduction to neural computing – Chapman & Hall
4. Artificial Neural Networks – Robert J. Schalkoff, McGraw Hill
5. Artificial Neural Networks – B.Yegnanarayana, PHI