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

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

Generalization, Discrimination, and Extinction

Generalization, Discrimination, and Extinction

Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...

You might also read

Related Articles

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

Sort by

Same author

A Strong and Simple Deep Learning Baseline for BCI Motor Imagery Decoding.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2024

Same author

Easy-Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components.

Journal of imaging·2022

Same author

Rethinking Weight Decay for Efficient Neural Network Pruning.

Journal of imaging·2022

Same author

Improved Visual Localization via Graph Filtering.

Journal of imaging·2021

Same author

Gradients of connectivity as graph Fourier bases of brain activity.

Network neuroscience (Cambridge, Mass.)·2021

Same author

Quantization and Deployment of Deep Neural Networks on Microcontrollers.

Sensors (Basel, Switzerland)·2021

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

Search research articles

Related Experiment Videos

Sparse neural networks with large learning diversity.

Vincent Gripon¹, Claude Berrou

¹Electronics Department, Télécom Bretagne (Institut Télécom), Brest, France. vincent.gripon@telecombretagne.eu

IEEE Transactions on Neural Networks

|June 10, 2011

Summary

This summary is machine-generated.

This study introduces novel coded recurrent neural networks (CRNNs) with three sparsity levels. These CRNNs demonstrate robust learning and recall capabilities, even with significant data loss.

Related Experiment Videos

Area of Science:

Computational Neuroscience
Machine Learning
Artificial Intelligence

Background:

Recurrent neural networks (RNNs) are powerful tools for sequential data processing.
Sparsity in neural networks can improve efficiency and robustness.
Existing RNN architectures may face challenges with high data loss scenarios.

Purpose of the Study:

To introduce a novel architecture of coded recurrent neural networks (CRNNs) with inherent multi-level sparsity.
To investigate the learning and recall capabilities of these CRNNs, particularly under conditions of data erasure.
To evaluate the performance of the proposed CRNNs as both classifiers and associative memories.

Main Methods:

Development of a coded recurrent neural network model utilizing binary neurons and binary connections.
Implementation of three distinct levels of sparsity: message size relative to neuron count, a coding rule for local neural activity constraint, and low final connection density post-learning.
Assessment of network performance through classification tasks and associative memory recall, including scenarios with significant data erasures.

Main Results:

The proposed simple binary CRNN architecture successfully learns and recalls a large number of messages.
The network exhibits remarkable resilience to strong data erasures, maintaining performance.
Effective utilization of the network as both a classifier and an associative memory was demonstrated.

Conclusions:

The introduced multi-level sparsity in CRNNs offers a simple yet effective approach for robust learning and recall.
Binary neural networks with controlled sparsity are a promising direction for memory and classification tasks, especially in noisy environments.
The CRNNs presented provide a computationally efficient and resilient model for handling data with significant erasures.