BayesPCN: A Continually Learnable Predictive Coding Associative Memory

05/20/2022
by   Jason Yoo, et al.
The University of British Columbia
0

Associative memory plays an important role in human intelligence and its mechanisms have been linked to attention in machine learning. While the machine learning community's interest in associative memories has recently been rekindled, most work has focused on memory recall (read) over memory learning (write). In this paper, we present BayesPCN, a hierarchical associative memory capable of performing continual one-shot memory writes without meta-learning. Moreover, BayesPCN is able to gradually forget past observations (forget) to free its memory. Experiments show that BayesPCN can recall corrupted i.i.d. high-dimensional data observed hundreds of "timesteps" ago without a significant drop in recall ability compared to the state-of-the-art offline-learned associative memory models.

READ FULL TEXT

page 2

page 8

page 16

page 17

06/08/2023

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

Few-shot meta-learning presents a challenge for gradient descent optimiz...
02/07/2019

Adaptive Posterior Learning: few-shot learning with a surprise-based memory module

The ability to generalize quickly from few observations is crucial for i...
10/20/2020

Learning to Learn Variational Semantic Memory

In this paper, we introduce variational semantic memory into meta-learni...
05/28/2021

Towards mental time travel: a hierarchical memory for reinforcement learning agents

Reinforcement learning agents often forget details of the past, especial...
05/07/2019

Continual and Multi-task Reinforcement Learning With Shared Episodic Memory

Episodic memory plays an important role in the behavior of animals and h...
12/02/2021

Wearable Affective Memory Augmentation

Human memory prioritizes the storage and recall of information that is e...
10/08/2022

An associative memory model with very high memory rate: Image storage by sequential addition learning

In this paper, we present a neural network system related to about memor...

Please sign up or login with your details

Forgot password? Click here to reset