A Growing Long-term Episodic & Semantic Memory

10/20/2016
by   Marc Pickett, et al.
0

The long-term memory of most connectionist systems lies entirely in the weights of the system. Since the number of weights is typically fixed, this bounds the total amount of knowledge that can be learned and stored. Though this is not normally a problem for a neural network designed for a specific task, such a bound is undesirable for a system that continually learns over an open range of domains. To address this, we describe a lifelong learning system that leverages a fast, though non-differentiable, content-addressable memory which can be exploited to encode both a long history of sequential episodic knowledge and semantic knowledge over many episodes for an unbounded number of domains. This opens the door for investigation into transfer learning, and leveraging prior knowledge that has been learned over a lifetime of experiences to new domains.

READ FULL TEXT

page 6

page 7

research
12/04/2021

Overcome Anterograde Forgetting with Cycled Memory Networks

Learning from a sequence of tasks for a lifetime is essential for an age...
research
07/06/2023

RecallM: An Architecture for Temporal Context Understanding and Question Answering

The ideal long-term memory mechanism for Large Language Model (LLM) base...
research
10/20/2020

Learning to Learn Variational Semantic Memory

In this paper, we introduce variational semantic memory into meta-learni...
research
09/01/2021

∞-former: Infinite Memory Transformer

Transformers struggle when attending to long contexts, since the amount ...
research
09/16/2017

Long-Term Ensemble Learning of Visual Place Classifiers

This paper addresses the problem of cross-season visual place classifica...
research
04/06/2023

Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories

One of the new developments in chit-chat bots is a long-term memory mech...
research
09/26/2018

Developmental Bayesian Optimization of Black-Box with Visual Similarity-Based Transfer Learning

We present a developmental framework based on a long-term memory and rea...

Please sign up or login with your details

Forgot password? Click here to reset