This document discusses using neural networks for software defect prediction. It examines the effectiveness of using a radial basis function neural network and a probabilistic neural network on prediction accuracy and defect prediction compared to other techniques. The key findings are that neural networks provide an acceptable level of accuracy for defect prediction but perform poorly at actual defect prediction. Probabilistic neural networks performed consistently better than other techniques across different datasets in terms of prediction accuracy and defect prediction ability. The document recommends using an ensemble of different software defect prediction models rather than relying on a single technique.