290 likes | 631 Views
Introduction to Artificial Neural Networks. Andrew L. Nelson Visiting Research Faculty University of South Florida. Overview. References Introduction History Biologically Inspired Applications The Perceptron Activation Functions Hidden Layer Networks Training with BP Examples.
E N D
Introduction to Artificial Neural Networks Andrew L. Nelson Visiting Research Faculty University of South Florida
Overview • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Outline to the left • Current topic in red • Introduction • History and Origins • Biologically Inspired • Applications • Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
References • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • W. S. McCulloch, W. Pitts, "A logical calculus of the ideas immanent in nervous activity," Bulletin of Mathematical Biophysics, vol. 5 pp. 115-133, 1943. • J. L. McClelland, D. E. Rumelhart, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, The MIT Press, 1986. • C. M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995. Neural Networks
Introduction • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Artificial Neural Networks (ANN) • Connectionist computation • Parallel distributed processing • Computational models • Biologically Inspired computational models • Machine Learning • Artificial intelligence Neural Networks
History • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • McCulloch and Pitts introduced the Perceptron in 1943. • Simplified model of a biological neuron • Fell out of favor in the late 1960's • (Minsky and Papert) • Perceptron limitations • Resurgence in the mid 1980's • Nonlinear Neuron Functions • Back-propagation training Neural Networks
Summary of Applications • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Function approximation • Pattern recognition • Signal processing • Modeling • Control • Machine learning Neural Networks
Biologically Inspired • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Electro-chemical signals • Threshold output firing Neural Networks
The Perceptron • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Binary classifier functions • Threshold activation function Neural Networks
The Perceptron: Threshold Activation Function • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Binary classifier functions • Threshold activation function Neural Networks
Linear Activation functions • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Output is scaled sum of inputs Neural Networks
Nonlinear Activation Functions • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Sigmoid Neuron unit function Neural Networks
Layered Networks • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples . Neural Networks
SISO Single Hidden Layer Network • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Can represent and single input single output functions: y = f(x) Neural Networks
Training Data Set • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Adjust weights (w) to learn a given target function: y = f(x) Given a set of training data X→Y Neural Networks
Training Weights: Error Back-Propagation (BP) • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Weight update formula: Neural Networks
Error Back-Propagation (BP) • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Training error term: e Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
BP Formulation • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Neural Networks
Example: The XOR problem: • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Single hidden layer: 3 Sigmoid neurons • 2 inputs, 1 output Desired I/O table (XOR): Neural Networks
Example: The XOR problem: • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Training error over epoch Neural Networks
Example: The XOR problem: • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples initial_weights = 0.0654 0.2017 0.0769 0.1782 0.0243 0.0806 0.0174 0.1270 0.0599 0.1184 0.1335 0.0737 0.1511 final_weights = 4.6970 -4.6585 2.0932 5.5168 -5.7073 -3.2338 -0.1886 1.6164 -0.1929 -6.8066 6.8477 -1.6886 4.1531 Neural Networks
Example: The XOR problem: • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples Mapping produced by the trained neural net: Neural Networks
Example: Overtraining • References • Introduction • History • Biologically Inspired • Applications • The Perceptron • Activation Functions • Hidden Layer Networks • Training with BP • Examples • Single hidden layer: 10 Sigmoid neurons • 1 input, 1 output Neural Networks