Self-organizing network system forming memory from nonstationary probability distributions

We propose an artificial neural system that forms memory by receiving input vectors obeying an unknown nonstationary probability density function (PDF). The system consists of a set of neural vector quantizers (NVQs), each of which can approximate nonstationary PDFs. Each NVQ exclusively learns a stationary piece of the nonstationary PDF and stores its approximated representation, where the nonstationary PDF consists of some stationary pieces. Experimental results show that the system has functions `memorization,' `retention,' and `recall' of information, which is required in memory systems. The results also illustrate that the system receives inputs from a nonstationary PDF and stores statistical information by distributing it equally over the system. As a result, the system would be considered a new model for biological memory. The system can also be used to model nonstationary phenomena. This ability is desirable for various applications, for example, process control, economical modeling, and so on.