A Hippocampus Model for Online One-Shot Storage of Pattern Sequences

05/30/2019
by   Jan Melchior, et al.
0

We present a computational model based on the CRISP theory (Content Representation, Intrinsic Sequences, and Pattern completion) of the hippocampus that allows to continuously store pattern sequences online in a one-shot fashion. Rather than storing a sequence in CA3, CA3 provides a pre-trained sequence that is hetero-associated with the input sequence, which allows the system to perform one-shot learning. Plasticity on a short time scale therefore only happens in the incoming and outgoing connections of CA3. Stored sequences can later be recalled from a single cue pattern. We identify the pattern separation performed by subregion DG to be necessary for storing sequences that contain correlated patterns. A design principle of the model is that we use a single learning rule named Hebbiand-escent to train all parts of the system. Hebbian-descent has an inherent forgetting mechanism that allows the system to continuously memorize new patterns while forgetting early stored ones. The model shows a plausible behavior when noisy and new patterns are presented and has a rather high capacity of about 40 CA3. One notable property of our model is that it is capable of `boot-strapping' (improving) itself without external input in a process we refer to as `dreaming'. Besides artificially generated input sequences we also show that the model works with sequences of encoded handwritten digits or natural images. To our knowledge this is the first model of the hippocampus that allows to store correlated pattern sequences online in a one-shot fashion without a consolidation process, which can instantaneously be recalled later.

READ FULL TEXT
research
06/07/2023

Long Sequence Hopfield Memory

Sequence memory is an essential attribute of natural and artificial inte...
research
02/01/2022

Content addressable memory without catastrophic forgetting by heteroassociation with a fixed scaffold

Content-addressable memory (CAM) networks, so-called because stored item...
research
07/03/2022

Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning

Few-shot class-incremental learning(FSCIL) focuses on designing learning...
research
09/01/2014

Storing sequences in binary tournament-based neural networks

An extension to a recently introduced architecture of clique-based neura...
research
10/07/2019

ER-index: a referential index for encrypted genomic databases

Huge DBMSs storing genomic information are being created and engineerize...
research
07/10/2023

Large Language Models as General Pattern Machines

We observe that pre-trained large language models (LLMs) are capable of ...
research
05/02/2011

Recalling of Images using Hopfield Neural Network Model

In the present paper, an effort has been made for storing and recalling ...

Please sign up or login with your details

Forgot password? Click here to reset