• Home
  • Search
  • Autonomous Learning With High-Dimensional Computing Architecture Similar to Von Neumann's.
  • https://doi.org/10.1162/neco.a.1523Copy DOI Icon

Autonomous Learning With High-Dimensional Computing Architecture Similar to Von Neumann's.

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

We model human and animal learning by computing with high-dimensional vectors (e.g., D = 10,000). The architecture resembles traditional (von Neumann) computing with numbers, but the instructions refer to vectors and operate on them in superposition. The architecture includes a high-capacity memory for vectors, counterpart of the random-access memory (RAM) for numbers. The model's ability to learn from data reminds us of deep learning, but with an architecture closer to biology. The architecture agrees with an idea from psychology that human memory and learning involve a short-term working memory and a long-term data store. Neuroscience provides us with a model of the long-term memory, namely, the cortex of the cerebellum. With roots in psychology, biology, and traditional computing, a theory of computing with vectors can help us understand how brains compute. Application to learning by robots seems inevitable, but there is likely to be more, including language. Ultimately we want to compute with no more material and energy than brains use. To that end, we need a mathematical theory that agrees with psychology and biology and is suitable for nano-technology. We also need to exercise the theory in large-scale experiments. The analogy with traditional computing suggests that the architecture be programmable in terms of variables, values, and data structures, the very things that have made traditional computing ubiquitous and that seem worth learning from and emulating.

Similar Papers
  • Conference Article
  • Citations2

Neuromorphic Array Communications Controller to Support Large-Scale Neural Networks

  • Jul 01, 2018
  • Aaron R Young +4
  • Conference Article
  • Citations2

"Data Structure" Online and Offline Hybrid New Engineering "Golden Course" Construction

  • May 25, 2021
  • Feng Liu +5
  • Conference Article
  • Citations1

Spatial regularization based on support tensor machine for neuroimaging classification

  • Jan 01, 2015
  • Yingjiang Wu +1
  • Book Chapter
  • Citations100

A “LEVELS OF ANALYSIS” VIEW OF MEMORY

  • Jan 01, 1973
  • Communication and Affect
  • Fergus I.M Craik
  • Research Article

Anti‐frequency long short‐term memory model for stable estimation of structural response under noise conditions

  • Sep 18, 2025
  • Computer-Aided Civil and Infrastructure Engineering
  • S Park +2
  • Book Chapter
  • Citations41

A Memory Model Based on the Siamese Network for Long-Term Tracking

  • Jan 01, 2019
  • Hankyeol Lee +2
  • Preprint Article

Application of Optimized 3D U-Net Residual Network with CBAM and MEGA Modules in Seismic Fault Detection

  • Mar 18, 2025
  • Yu Wang
  • Research Article
  • Citations7

Lower bounds on non-adaptive data structures maintaining sets of numbers, from sunflowers

  • Jun 22, 2018
  • Sivaramakrishnan Natarajan Ramamoorthy +1
  • Book Chapter

The role of time in human memory and bindingA review of the evidence

  • Jun 22, 2006
  • Gordon D A Brown +1
  • Conference Article
  • Citations53

A locality-preserving cache-oblivious dynamic dictionary

  • Jan 06, 2002
  • Michael A Bender +3
  • Dissertation

CMOS interface circuits for spin tunneling junction based magnetic random access memories

  • Jan 01, 2002
  • Ganesh Saripalli
  • Research Article
  • Citations13

Enabling efficient analysis of biobank-scale data with genotype representation graphs.

  • Dec 05, 2024
  • Nature computational science
  • Drew Dehaas +2
  • Research Article
  • Citations3

All digital realization of logarithm automatic gain control loop

  • Nov 01, 2009
  • Journal of ZheJiang University (Engineering Science)
  • Yang Zhi-Min Bang Xiao-Shuang
  • Supplementary Content

Architecting Query Compilers for Diverse Workloads

  • Jun 10, 2019
  • Figshare
  • Ruby Y Tahboub
  • Research Article
  • Citations35

Neural Autoassociative Memories for Binary Vectors: A Survey

  • Jun 12, 2017
  • Kibernetika i vyčislitelʹnaâ tehnika
  • Volodymyr Gritsenko +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.