GATE: Adaptive Learning with Working Memory by Information Gating in Multi-lamellar Hippocampal Formation

TL;DR

GATE is a biologically inspired model that mimics hippocampal formation mechanisms to achieve rapid generalization and flexible working memory through a multi-lamellar architecture and information gating.

Contribution

This work introduces GATE, a novel multi-lamellar hippocampal-inspired model that captures flexible memory and generalization, aligning with experimental neural recordings.

Findings

GATE forms neural representations similar to biological hippocampal cells.

The model demonstrates rapid generalization across changing environments and tasks.

GATE provides insights into hippocampal memory mechanisms and supports brain-inspired AI development.

Abstract

Hippocampal formation (HF) can rapidly adapt to varied environments and build flexible working memory (WM). To mirror the HF's mechanism on generalization and WM, we propose a model named Generalization and Associative Temporary Encoding (GATE), which deploys a 3-D multi-lamellar dorsoventral (DV) architecture, and learns to build up internally representation from externally driven information layer-wisely. In each lamella, regions of HF: EC3-CA1-EC5-EC3 forms a re-entrant loop that discriminately maintains information by EC3 persistent activity, and selectively readouts the retained information by CA1 neurons. CA3 and EC5 further provides gating function that controls these processes. After learning complex WM tasks, GATE forms neuron representations that align with experimental records, including splitter, lap, evidence, trace, delay-active cells, as well as conventional place cells. Crucially, DV architecture in GATE also captures information, range from detailed to abstract, which enables a rapid generalization ability when cue, environment or task changes, with learned representations inherited. GATE promises a viable framework for understanding the HF's flexible memory mechanisms and for progressively developing brain-inspired intelligent systems.