Indeterminate Probability Neural Network

Tao Yang, Chuang Liu, Xiaofeng Ma, Weijia Lu, Ning Wu, Bingyang Li, ZHIFEI YANG, Peng Liu, Lin Sun, xiaodong Zhang, Can Zhang

Keywords: Indeterminate Probability, Discrete Random Variable, Unsupervised Clustering, Classification, IPNN

Abstract: We propose a new general model called IPNN - Indeterminate Probability Neural Network, which combines neural network and probability theory together. In the classical probability theory, the calculation of probability is based on the occurrence of events, which is hardly used in current neural networks. In this paper, we propose a new general probability theory, which is an extension of classical probability theory, and makes classical probability theory a special case to our theory. With this new theory, some intractable probability problems have now become tractable (analytical solution). Besides, for our proposed neural network framework, the output of neural network is defined as probability events, and based on the statistical analysis of these events, the inference model for classification task is deduced. IPNN shows new property: It can perform unsupervised clustering while doing classification. Besides, IPNN is capable of making very large classification with very small neural network, e.g. model with 100 output nodes can classify 10 billion categories. Theoretical advantages are reflected in experimental results.

TLDR: We propose a new general probability theory, and some intractable probability problems have now become analytically tractable using this new theory.

Submission Number: 649