In this paper we report a Monte Carlo study of the dyanmics of large untrained, feedforward, neural networks with randomly chosen weights and feedback. The analysis consists of looking at the percent of the systems that exhibit chaos, the distribution of largest Lyapunov exponents, and the distrubution of correlation dimensions. As the systems become more complex (increasing inputs and neurons), the probability of chaos approaches unity. The correlation dimension is typically much smaller than the system dimension.
展开▼