Storing sequences in binary tournament-based neural networks
This work addresses sequence storage for neural network models, offering biological plausibility, but appears incremental as an extension to an existing architecture.
The paper tackles the problem of storing sequences efficiently in neural networks by extending a clique-based architecture with oriented connections and flexible redundancy, achieving high efficiency in sequence storage and retrieval.
An extension to a recently introduced architecture of clique-based neural networks is presented. This extension makes it possible to store sequences with high efficiency. To obtain this property, network connections are provided with orientation and with flexible redundancy carried by both spatial and temporal redundancy, a mechanism of anticipation being introduced in the model. In addition to the sequence storage with high efficiency, this new scheme also offers biological plausibility. In order to achieve accurate sequence retrieval, a double layered structure combining hetero-association and auto-association is also proposed.