Course Outline

              ● Psychology and its relation to neural networks

              ● Models of Artificial Neural Networks

              ● Learning rules

              ● Single -layer perceptron classifiers

              ● Perceptron Convergence Theorem

              ● Multilayer Feed-forward networks

              ● Error Back-Propagation Training, and how to enhance it

              ● Structure selection

              ● Functional link networks

              ● Performance Optimization, and Conjugate Gradient Algorithm

              ● Universal Approximation Theorems, and NNs as Universal  Approximators

              ● The Radial Basis Function Networks

              ● Single-layer feedback networks

              ● Hopfield networks (Discrete-Time, and Gradient-Type)

              ● Recurrent auto-associative memory

              ● Discrete, Continuous, and Adaptive Bidirectional Associative Memory (BAM)

              ● Two Coding Strategies for Bidirectional (Multiple training, and Dummy Augmentation)

              ● Multidirectional Associative Memory (MAM), and Temporal Associative Memory (TAM)

              ● Neural Networks based on Principal Components Analysis (PCA)

              ● Hamming nets and MAXNET

              ● Unsupervised learning of clusters, and Kohonen Network

              ● Self-Organizing Maps (SOM)

              ● Learning Vector Quantization (LVQ)

              ● Counter-Propagation Network (CPN)

              ● Adaptive Resonance Theory (ART)

              ● MATLAB Neural Network Toolbox

              ● Applications of neural algorithms and systems (Control, Robotics, Pattern/Character recognition, Adaptive noise cancellation, etc.)

              ● New (applied/theoretical) emerging topics will be covered in the final projects