Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A neural computation model with short-term memory.

M D Tom¹, M F Tenorio

¹Parallel Distributed Structure Lab., Purdue Univ., West Lafayette, IN.

IEEE Transactions on Neural Networks

|January 1, 1995

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The ClusNet algorithm and time series prediction.

International journal of neural systems·1993

Same author

Self-organizing network for optimum supervised learning.

IEEE transactions on neural networks·1990

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces the hystery model, a novel neuron architecture inspired by brain memory. This model exhibits hysteresis-like loops, enabling adaptive memory for complex temporal patterns in neural computation.

Area of Science:

Computational Neuroscience
Artificial Intelligence
Materials Science

Background:

Understanding brain memory mechanisms is crucial for advancing neural computation.
Existing computational models may not fully capture the dynamic, history-dependent nature of neural responses.

Purpose of the Study:

To propose a new neuron architecture, the hystery model, inspired by brain memory characteristics.
To investigate the potential of hysteresis loops in describing neural responses and enabling adaptive memory.

Main Methods:

Developed a novel neuron architecture based on generalized sigmoid curves to form hysteresis loops.
Theorized and mathematically proved the convergence of the hystery model's response to hysteresis-like loops.
Applied the model to temporal pattern discrimination tasks to demonstrate its memory capabilities.

Related Experiment Videos

Main Results:

The hystery model effectively mimics hysteresis loops, with memory capacity adapting to input sequence length.
Demonstrated nonlinear short-term memory characteristics through temporal pattern discrimination.
The model's response converges asymptotically to hysteresis-like loops.

Conclusions:

The hystery model offers a new paradigm for neural computation with adaptive, history-dependent memory.
Potential applications include advanced control systems, signal processing, and spatiotemporal pattern recognition.
Leveraging semiconductor hysteresis phenomena could further enhance this model's capabilities.