Entropic associative memory for real world images

TL;DR

This paper demonstrates that the entropic associative memory (EAM) model effectively stores, recognizes, and retrieves complex real-world images like animals and vehicles, generating meaningful associative chains.

Contribution

It extends the application of EAM to complex, unconventional images, showing its capability for realistic memory tasks beyond structured data.

Findings

EAM successfully stores and recognizes complex images.

EAM generates meaningful associative retrieval chains.

Retrieved images can serve as memories or imaginative products.

Abstract

The entropic associative memory (EAM) is a computational model of natural memory incorporating some of its putative properties of being associative, distributed, declarative, abstractive and constructive. Previous experiments satisfactorily tested the model on structured, homogeneous and conventional data: images of manuscripts digits and letters, images of clothing, and phone representations. In this work we show that EAM appropriately stores, recognizes and retrieves complex and unconventional images of animals and vehicles. Additionally, the memory system generates meaningful retrieval association chains for such complex images. The retrieved objects can be seen as proper memories, associated recollections or products of imagination.