Organization of artificial neural network (ANN) for identification of alternative translation initiation sites (aTIS). To identify aTISs, this study used a feed-forward back-propagation ANN using Matlab's Neural Network toolbox. Artificial Neural Networks are a computational algorithm that uses layers of neurons with weighted edges connecting each layer to perform classification. To determine the specific ANN architecture, this study started with a static training set and modified the number of neurons in the hidden layer of the ANN as well as the activation function used for the neurons in each layer. The resulting ANN contained 10 neurons in the input layer, 20 neurons in the hidden layer and a single output neuron. Inputs to the ANN are normalized in order to negate the effect of measurements in different ranges. The output neuron provides values in the range [0, 1].