úÎ74¿,      !"#$%&'()*+Our Artificial Neuron type ICreates a Neuron with the given threshold, weights and transfer function Equivalent to `createNeuronU t ws heavyside' Equivalent to `createNeuronU t ws sigmoid' aSame as createNeuronU, with a list instead of an UArr for the weights (converted to UArr anyway) jSame as createNeuronHeavysideU, with a list instead of an UArr for the weights (converted to UArr anyway) hSame as createNeuronSigmoidU, with a list instead of an UArr for the weights (converted to UArr anyway) The Heavyside function The Sigmoid function 7Computes the output of a given Neuron for given inputs 7Computes the output of a given Neuron for given inputs pTrains a neuron with the given sample, of the form (inputs, wanted_result) and the given learning ratio (alpha) LTrains a neuron with the given samples and the given learning ratio (alpha) LTrains a neuron with the given samples and the given learning ratio (alpha)     vCreates a layer compound of n neurons with the Sigmoid transfer function, all having the given threshold and weights. xCreates a layer compound of n neurons with the Heavyside transfer function, all having the given threshold and weights. vCreates a layer compound of n neurons with the sigmoid transfer function, all having the given threshold and weights. vCreates a layer compound of n neurons with the sigmoid transfer function, all having the given threshold and weights. 1Computes the outputs of each Neuron of the layer 1Computes the outputs of each Neuron of the layer FTrains each neuron with the given sample and the given learning ratio FTrains each neuron with the given sample and the given learning ratio GTrains each neuron with the given samples and the given learning ratio GTrains each neuron with the given samples and the given learning ratio :Returns the quadratic error of a layer for a given sample :Returns the quadratic error of a layer for a given sample     !@Computes the output of the given neural net on the given inputs "@Computes the output of the given neural net on the given inputs #FReturns the quadratic error of the neural network on the given sample $FReturns the quadratic error of the neural network on the given sample %GReturns the quadratic error of the neural network on the given samples &GReturns the quadratic error of the neural network on the given samples '}Train the given neural network using the backpropagation algorithm on the given sample with the given learning ratio (alpha) (}Train the given neural network using the backpropagation algorithm on the given sample with the given learning ratio (alpha) )*ÛTrain the given neural network on the given samples using the backpropagation algorithm using the given learning ratio (alpha) and the given desired maximal bound for the global quadratic error on the samples (epsilon) +ÛTrain the given neural network on the given samples using the backpropagation algorithm using the given learning ratio (alpha) and the given desired maximal bound for the global quadratic error on the samples (epsilon)  !"#$%&'()*+  !"#$%&'()*+  !"#$%&'()*+,      !"#$%&'()*+,-./hnn-0.1 AI.HNN.Neuron AI.HNN.Layer AI.HNN.NetNeuron thresholdweightsfunc createNeuronUcreateNeuronHeavysideUcreateNeuronSigmoidU createNeuroncreateNeuronHeavysidecreateNeuronSigmoid heavysidesigmoidcomputeUcompute learnSampleU learnSample learnSamplesU learnSamplescreateSigmoidLayerUcreateHeavysideLayerUcreateSigmoidLayercreateHeavysideLayer computeLayerU computeLayerlearnSampleLayerUlearnSampleLayerlearnSamplesLayerUlearnSamplesLayer quadErrorU quadErrorchecknn computeNetU computeNet quadErrorNetU quadErrorNetglobalQuadErrorNetUglobalQuadErrorNet backPropUbackProptrainAuxtrainUtrain