Presentation is loading. Please wait.

Presentation is loading. Please wait.

Applications of Neural Networks Patrick Stalcup. Overview Background Vocabulary The Math Data Structure Design Black Boxing Example Applications.

Similar presentations


Presentation on theme: "Applications of Neural Networks Patrick Stalcup. Overview Background Vocabulary The Math Data Structure Design Black Boxing Example Applications."— Presentation transcript:

1 Applications of Neural Networks Patrick Stalcup

2 Overview Background Vocabulary The Math Data Structure Design Black Boxing Example Applications

3

4 Vocabulary Neuron - A node in our Neural Network; Has Direction Neural Network - A collection of Nodes that has a top and a bottom, with connections between the nodes Sigmoid Function - A function that normalizes the values of the neurons Feed-forward evaluation - Evaluating the network from top to bottom, 'feeding' the values from the first nodes to the last Error Back Propagation - Passing the error from the output back up the network; the opposite of feed-forward

5 Background Based on Organic Structures First experiment on in the 1960's Rapid development in the 1980's as more powerful computers came in to use Used to 'teach' computers about complex situations that have a limited set of choices

6 The Math Sigmoid(x) = 1.0/(1.0+e^(-x)) dSigmoid/dx = (1.0+Sigmoid(x))*Sigmoid(x) Error = Σ (1/2)*(Actual-Theoretical)^2 dError/dOutput = Σ (Actual - Theoretical) dWeight/dError = PreviousError* Σ (Inputs) dWeight/dOutput = dError/dOutput

7

8 Abstract Data Type Based on graph theory Called a 'directed graph' Nodes that have connections to other nodes with weights on those connections

9 Black Boxing Neural Networks are very hard to code reliably My Neural network Library (nnlib.h) offers an easy way for programmers to utilize Neural Networks in C #include "nnlib.h"... int layers[3] = {2,3,1}; int test_in[4][2] = {{0,0},{1,1},{0,1},{1,0}}; int test_out[4] = {0,0,1,1}; int main(int argv,char **args) { network n; init_network(n,layers,3); train_network(n,test_in,test_out,4,10000); print_output(n); }

10 Example Applications Board Game Heuristics Optical Character Recognition Music Genre Identification Mathematical Modelling


Download ppt "Applications of Neural Networks Patrick Stalcup. Overview Background Vocabulary The Math Data Structure Design Black Boxing Example Applications."

Similar presentations


Ads by Google