Neuroet is an easy-to-use artificial neural network (NN) package designed to assist with determining relationships among variables in complex ecological and biological systems. The package, which is available for download from the web site http://noble.ce.washington.edu, features a procedure to optimize the architecture of NNs by adjusting the number of neurons in the hidden layer, and a novel procedure to identify the input variable, or combinations of input variables, that is/are important for predicting outputs. The package also includes a method to extract equations defining relationships among the data (independent of the NN package). The performance of Neuroet was assessed using benchmark standards for NNs. An example of the program's utility is provided using an environmental data set.