Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory

arXiv:2404.11870v1 Announce Type: new
Abstract: We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neural memory that uses novel physical addresses and pointer manipulation techniques to mimic human and computer symbol processing abilities. PANM facilitates pointer assignment, dereference, and arithmetic by explicitly using physical pointers to access memory content. Remarkably, it can learn to perform these operations through end-to-end training on sequence data, powering …

abstract apply arxiv computer cs.cl cs.lg data human manipulation memory networks neural networks novel processing type