INCREMENTAL LEARNING OF COMPLEX TEMPORAL PATTERNS

A neural model for temporal pattern generation is used and analyzed fo r training with multiple complex sequences in a sequential manner. The network exhibits some degree of interference when new sequences are a cquired, It is proven that the model is capable of incrementally learn ing a finite number of complex sequences. The model is then evaluated with a large set of highly correlated sequences. While the number of i ntact sequences increases linearly with the number of previously acqui red sequences, the amount of retraining due to interference appears to be independent of the size of existing memory. The model is extended to include a chunking network which detects repeated subsequences betw een and within sequences. The chunking mechanism substantially reduces the amount of retraining in sequential training. Thus, the network in vestigated here constitutes an effective sequential memory, Various as pects of such a memory are discussed.