biopython v1.71.0 Bio.NeuralNetwork.BackPropagation.Network.BasicNetwork

Represent a Basic Neural Network with three layers.

This deals with a Neural Network containing three layers:

  • Input Layer
  • Hidden Layer
  • Output Layer

Link to this section Summary

Functions

Initialize the network with the three layers

Predict outputs from the neural network with the given inputs

Train the neural network to recognize particular examples

Link to this section Functions

Initialize the network with the three layers.

Predict outputs from the neural network with the given inputs.

This uses the current neural network to predict outputs, no training of the neural network is done here.

Train the neural network to recognize particular examples.

Arguments:

  • training_examples — A list of TrainingExample classes that will be used to train the network.
  • validation_examples — A list of TrainingExample classes that are used to validate the network as it is trained. These examples are not used to train so the provide an independent method of checking how the training is doing. Normally, when the error from these examples starts to rise, then it’s time to stop training.
  • stopping_criteria — A function, that when passed the number of iterations, the training error, and the validation error, will determine when to stop learning.
  • learning_rate — The learning rate of the neural network.
  • momentum — The momentum of the NN, which describes how much of the prevoious weight change to use.