ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2205.09930
77
9

BayesPCN: A Continually Learnable Predictive Coding Associative Memory

20 May 2022
Jason Yoo
F. Wood
    KELM
ArXivPDFHTML
Abstract

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 (readreadread) over memory learning (writewritewrite). 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 (forgetforgetforget) to free its memory. Experiments show that BayesPCN can recall corrupted i.i.d. high-dimensional data observed hundreds to a thousand ``timesteps'' ago without a large drop in recall ability compared to the state-of-the-art offline-learned parametric memory models.

View on arXiv
Comments on this paper