Software engineering effort models using neural networks

The authors discuss and demonstrate the use of neural network (NN) techniques for constructing software engineering effort models using the backpropagation and self-organizing neural network (SONN) algorithms. NN models have some important properties which are advantageous in this context, including the distribution free property, the learning capability, and the ease of parallel implementations. It is demonstrated experimentally that NN techniques are superior in performance, learning time, and modeling power, and require fewer prior assumptions than traditional software engineering techniques. In addition, the SONN algorithm also gives an algebraic representation of the network model which can help researchers identify factors that may be important to the process under study