Abstract
An analog model neural network that can solve a general problem of recognizing patterns in a time-dependent signal is presented. The networks use a patterned set of delays to collectively focus stimulus sequence information to a neural state at a future time. The computational capabilities of the circuit are demonstrated on tasks somewhat similar to those necessary for the recognition of words in a continuous stream of speech. The network architecture can be understood from consideration of an energy function that is being minimized as the circuit computes. Neurobiological mechanisms are known for the generation of appropriate delays.
Keywords
Computer scienceArtificial neural networkComputationStimulus (psychology)Set (abstract data type)Time delay neural networkModels of neural computationActivation functionFocus (optics)Artificial intelligenceAlgorithm
Affiliated Institutions
Related Publications
Average consensus problems in networks of agents with delayed communications
The present paper is devoted to the study of average consensus problems for undirected networks of dynamic agents having communication delays. The accent is put here on the stud...
Consensus and Cooperation in Networked Multi-Agent Systems
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper provides a theoretical framework for analysis of consensus algorithms...
INFORMATION THEORY AND STIMULUS‐INDEPENDENT THOUGHT
The production of stimulus‐independent thought (e.g. fantasy and imagery) was measured as a function of the rate at which information was presented to human subjects. Informatio...
Loihi: A Neuromorphic Manycore Processor with On-Chip Learning
Loihi is a 60-mm2 chip fabricated in Intels 14-nm process that advances the state-of-the-art modeling of spiking neural networks in silicon. It integrates a wide range of novel ...
A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cel...
Publication Info
- Year
- 1987
- Type
- article
- Volume
- 84
- Issue
- 7
- Pages
- 1896-1900
- Citations
- 357
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
357
OpenAlex
Cite This
David W. Tank,
J. J. Hopfield
(1987).
Neural computation by concentrating information in time..
Proceedings of the National Academy of Sciences
, 84
(7)
, 1896-1900.
https://doi.org/10.1073/pnas.84.7.1896
Identifiers
- DOI
- 10.1073/pnas.84.7.1896