University of Toronto Mathematics Network
Question Corner and Discussion Area

Use of Neural Networks for Empirical Data

I am currently working on a thesis on group dynamics. In my attempt to quantify qualitative research (i.e. interpret responses to interview questions), I am resorting to the development of neural networks. My question relates to the utility of neural networks in empirical studies. Could you direct me to resources that would enable me to implement the proper formation of neural networks, and their respective instruments for testing hypotheses (i.e equations) that emerge from such models. Furthermore, how can fuzzy logic be utilized in conjunction to neural networks.

It is a little unclear to me what the question is about. But I can certainly recommend an introduction to neural networks. Hertz, Krogh and Palmers "Introduction to the theory of neural computation" is in my opinion by far the best introduction, although I guess a little dated by now. It requires a certain level of mathematical sophistication. Of more recent books there is (physicist) Chris Bishop "Statistical learning in neural networks" and a book by (statistician) Brian Ripley with roughly the same title. Let me know if you have trouble locating any of these and I'll send you proper references.