OBJECTIVE: This course aims at giving a foundation of Artificial Neural Networks,which has 99EEn used extensively to solve many electrical and control problems.
Objectives - History- Biological Inspiration- Neuron Model- Single- Input Neuron-Multi-Input Neuron- Network Architectures- A Layer of Neurons-Multiple Layers of Neurons.
Perceptron Architecture- Single-Neuron Perceptron- Multi-Neuron Perceptron- Perceptron Learning Rule- Constructing Learning Rules- Training Multiple-Neuron Perceptrons.
Simple Associative Network- Unsupervised Hebb Rule- Hebb Rule with Decay-Instar Rule- Kohonen Rule.
Adaline Network- Single Adaline- Mean Square Error- LMS Algorithm- Analysis of Convergence- Adaptive Filtering- Adaptive Noise Cancellation-Echo Cancellation.
Hopfield Model- Lyapunov Function- Invariant Sets-Examples- Hopfield Attractors- Hopfield Design- Content - Addressable Memory- Liapunov Surface.