Correlation Matrix Memory

is learned, it is stored in the brain, from e recalled later when required. Memory G y be d i v i d m t e r m ’ ” x m o r y , depending on the retention time (Arbib, 1989). Short-term memory refers to a compilation of knowledge representing the “current” state of the environment. Any discrepancies between knowledge stored in short-term memory and a “new” state are used to update the short-term memory. Long-term memory, on the other hand, refers to knowledge stored for a long time or permanently. In this chapter we study a brainlike distributed memory that operates by association, which is rather simple to understand and yet fundamental in its operation. Indeed, association has been known to be a prominent feature of human memory since Aristotle, and all models of cognition use association in one form or another as the basic operation (Anderson, 1985). For obvious reasons, this kind of memory is called associative memory. A fundamental property of associative memory is that it maps an output pattern of neural activity onto an input pattern of neural activity. In particular, during the learning phase, a key pattern is presented as stimulus, and the memory transforms it into a memorized or storedpattern. The storage takes place through specific changes in the synaptic weights of the memory. During the retrieval or recall phase, the memory is presented with a stimulus that is a noisy version or an incomplete description of a key pattern originally associated with a stored pattern. Despite imperfections in the stimulus, the associative memory has the capability to recall the stored pattern correctly. Accordingly, associative memories are used in applications such as pattern recognition, to recover data when the available information is imprecise. From this brief exposition of associative memory, we may identify the following characteristics of this kind of memory: