PHM 802

Lectures 2011
Lecture 1: Neural Networks: A Natural Way to Compute
Lecture 2: Neuroscience Briefer
Lecture 3: Math Primer for Neural Networks
Lecture 4: Artificial Neurons and Signal Functions
Lecture 5: Probabilistic Signal Functions, Monte Carlo Simulation, Architectures
Lecture 6: Pattern Classification, Linear Separability Boolean Functions
Lecture 7: Threshold Logic Neuron Classifiers
Lecture 8: (A) TLN Classifiers for Non-Linearly Separable and Complex Problems
Lecture 9: (B) Capacity of Threshold Logic Neuron (Optional)
Lecture 10: Automated Learning Procedure for TLN’s
Lecture 11: Perceptron Learning in Weight Space and an Example
Lecture 12: Perceptron Convergence Theorem and Proof with a MATLAB Example
Lecture 13: Tutorial I
Lecture 14: Alpha-Least Mean Square Learning in Linear Neurons with a MATLAB Example
Lecture 15: Mean Square Error, Weiner Solution, and Visualization in MATLAB
Lecture 16: Steepest Descent with MATLAB Simulation
Lecture 17: Mu-Least Mean Square Learning for Stochastic Data Streams with MATLAB Simulation
Lecture 18: Adaptive Noise Cancellation Application and Tutorial II
Lecture 19: Learning in Multilayered Feedforward Neural Networks
Lecture 20: Back propagation Learning Algorithm and MATLAB Simulation
Lecture 21: Back propagation Learning – Handworked Example
Lecture 22: Recap of Back propagation Learning, More Examples, and Universal Function Approximation
Lecture 23: Dynamical Systems Review
Lecture 24: More Dynamical Systems, Lyapunov Stability, and Neurodynamical Systems
Lecture 25: Orthogonal Linear Associative Memory
Lecture 26: Hopfield Associative Memory in Continuous Time
Lecture 27: Hopfield Associative Memory in Discrete Time
Lecture 28: Hopfield Network Numerical Example with Simulation
Lecture 29: Signal-Noise Decomposition and MATLAB Simulation of Hopfield Network
Lecture 30: Bidirectional Associative Memory
1 of 2
Previous Lesson
Next Lesson

Lecture 29: Signal-Noise Decomposition and MATLAB Simulation of Hopfield Network

Post a comment

Leave a Comment

Your email address will not be published. Required fields are marked *