Biological motivation: McCulloch-Pitts Neuron, brain organization, biological neurons; Single layer Perceptron: Learning and generalization, Hebbian contribution, Gradient Descent Learning, Widrow Delta rule; Multi-layer perceptrons (MLPs): learning in MLPs, Back-propagation algorithm, feed-forward network training, conjugate Gradient Learning, computational power of MLPs, Brain modeling, real world applications; Bias: statistical of view of network training, bias and variance, Under-Fitting and Over-Fitting, Bias/Variance trade-off, improving generalisation; Radial basis function networks: Introduction, Algorithms, Applications; Self-organizing techniques: topographic Maps, Kohenen Networks, components of self organization, SOM Architecture and Algorithms; Committee Machines: ensemble averaging, Boosting, Mixtures of experts; learning vector quantization (LVQ): Encoder-Decoder Model, Voronoi Tessellation; Advanced Topics overview: Recurrent Networks, Hopfield Model, Boltzmann machine, Adaptive Resonance Theory (ART), Evolving Neural Networks.
- editing-lecturer: Jeremiah Onunga