Neural networks and physical systems with emergent collective computational abilities.
Нейронные сети и физические системы с возникающими коллективными вычислительными способностями.
1982-04-01
SCID: 54.1/yq2tf4hj
Discuss with AI
asynchronous parallel processingcontent-addressable memoryemergent collective computationerror correctionfamiliarity recognition
Figures from the paper
Abstract (AI)
Computational properties of use of biological organisms or to the construction of computers can emerge as collective properties of systems having a large number of simple equivalent components (or neurons). The physical meaning of content-addressable memory is described by an appropriate phase space flow of the state of a system. A model of such a system is given, based on aspects of neurobiology but readily adapted to integrated circuits. The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size. The algorithm for the time evolution of the state of the system is based on asynchronous parallel processing. Additional emergent collective properties include some capacity for generalization, familiarity recognition, categorization, error correction, and time sequence retention. The collective properties are only weakly sensitive to details of the modeling or the failure of individual devices.
Key Findings
1
A system of many simple equivalent components can exhibit emergent collective computational properties useful for biological organisms and computers.
2
Collective properties of the model are robust and only weakly sensitive to modeling details or failures of individual components.
3
Content-addressable memory is realized as a phase space flow of system states, enabling retrieval of entire memories from sufficiently large partial inputs.
4
The model demonstrates emergent abilities including generalization, familiarity recognition, categorization, error correction, and time-sequence retention.
5
The proposed model, inspired by neurobiology and adaptable to integrated circuits, implements asynchronous parallel time evolution of system state.
Research Object
A model neural network / physical system composed of many simple equivalent components (neurons) implementing collective computation and content-addressable memory
Research Subject
Emergent collective computational properties of the system, specifically content-addressable memory retrieval from partial cues, and related behaviors (generalization, familiarity recognition, categorization, error correction, time-sequence retention) under asynchronous parallel dynamics and robustness to component failure
Publication Details
Publication Date
1982-04-01
Journal
Publisher
ISSN
Cited by
22910
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
Cited by20
Reducing the Dimensionality of Data with Neural Networks2006
The Graph Neural Network Model2008
Artificial neural networks: a tutorial1996
Machine Learning in Agriculture: A Review2018
Machine Learning for Fluid Mechanics2019
A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure–ground organization.2012
A comprehensive survey on machine learning for networking: evolution, applications and research opportunities2018
A Unifying Review of Deep and Shallow Anomaly Detection2021
Machine learning & artificial intelligence in the quantum domain: a review of recent progress2018
Dynamical principles in neuroscience2006
Knowledge Graph Embedding for Link Prediction: A Comparative Analysis2021
Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing2021
Potential, challenges and future directions for deep learning in prognostics and health management applications2020
A Digital Twin predictive maintenance framework of air handling units based on automatic fault detection and diagnostics2022
A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges2025
Accelerating scientific discovery with Co-Scientist2026
Artificial Intelligence and Advanced Materials2022
Nonlinear dynamics of the brain: emotion and cognition2010
Deep echo state networks with uncertainty quantification for spatio‐temporal forecasting2018
Electrorheological damper with annular ducts for seismic protection applications1996