Artificial Neural Network

Requirements:

• environment variable 'ANN_COMMAND' set to the executable.
• parameter 'seed' initializes a random number generator used to assign random values to network weights before training begins. Defaults to 42.
• parameter 'lrate' Learning Rate sets the rate at which the network converges to (learns) a model. The value of learning rate tends to produce a tradeoff in the number of iterations required to converge to a solution versus the overall quality of the solution. Defaults to 0.002 and must be in the range [0, 1].
• parameter 'numIterations' Each iteration is also referred to as an epoch. An epoch occurs after each pattern (datum) has been presented to the network and prediction errors have been backpropagated through the network to update network weights. The order in which patterns are presented is randomly rearranged after each epoch. Defaults to 10000.
• parameter 'hiddenUnits' Space separated list of integers, each > 0, may be empty. The network may contain zero or more layers of hidden units and each hidden layer may have one or more hidden units. Defaults to '' (no hidden units).

The ANN is wrapped around the back-propogation neural network code from the University of Wisconsin - Madison.

[To Be Added]