Coupled Neural Associative Memories
This work addresses a fundamental challenge in neural networks for robust memory storage and retrieval, with potential applications in AI and neuroscience, though it appears incremental in improving existing architectures.
The authors tackled the problem of designing neural associative memories that can learn many patterns and recall them accurately despite noise, achieving drastically better noise elimination and maintaining exponential pattern capacity compared to prior approaches.
We propose a novel architecture to design a neural associative memory that is capable of learning a large number of patterns and recalling them later in presence of noise. It is based on dividing the neurons into local clusters and parallel plains, very similar to the architecture of the visual cortex of macaque brain. The common features of our proposed architecture with those of spatially-coupled codes enable us to show that the performance of such networks in eliminating noise is drastically better than the previous approaches while maintaining the ability of learning an exponentially large number of patterns. Previous work either failed in providing good performance during the recall phase or in offering large pattern retrieval (storage) capacities. We also present computational experiments that lend additional support to the theoretical analysis.