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

Parallel Processing

Parallel Processing

The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...

You might also read

Related Articles

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

Sort by

Same author

Efficient robot navigation inspired by honeybee learning flights.

Nature·2026

Same author

All eyes, no IMU: learning flight attitude from vision alone.

npj Robotics·2026

Same author

Editorial: Algorithm-hardware co-optimization in neuromorphic computing for efficient AI.

Frontiers in neuroscience·2025

Same author

Adaptively Pruned Spiking Neural Networks for Energy-Efficient Intracortical Neural Decoding.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Same author

Bioinspired adaptive visual servoing control for quadrotors.

Bioinspiration & biomimetics·2025

Same author

The neurobench framework for benchmarking neuromorphic computing algorithms and systems.

Nature communications·2025

Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 11, 2025

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

Event-based optical flow on neuromorphic processor: ANN vs. SNN comparison based on activation sparsification.

Yingfu Xu¹, Guangzhi Tang², Amirreza Yousefzadeh³

¹Hardware-Efficient Artificial Intelligence Team, Stichting imec Nederland, High Tech Campus 31, Eindhoven, 5656 AA, The Netherlands.

Neural Networks : the Official Journal of the International Neural Network Society

|April 17, 2025

Summary

This summary is machine-generated.

Spiking neural networks (SNNs) demonstrate superior computational efficiency for event-based optical flow compared to artificial neural networks (ANNs). This is achieved through novel sparsification techniques and the SENECA neuromorphic processor, reducing both time and energy consumption.

Keywords:

Activation sparsification Benchmarking Event-based optical flow Neuromorphic computing Spiking neural networks

More Related Videos

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Published on: July 9, 2020

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

Related Experiment Videos

Last Updated: May 11, 2025

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

Published on: July 9, 2020

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

Area of Science:

Neuromorphic Engineering
Computer Vision
Artificial Intelligence

Background:

Spiking neural networks (SNNs) are proposed as more computationally efficient than artificial neural networks (ANNs) for event-based optical flow.
A lack of fair comparison studies in existing literature necessitates further investigation into SNN efficiency.

Purpose of the Study:

To conduct a fair comparison of computational efficiency between SNNs and ANNs for event-based optical flow.
To introduce a novel event-based optical flow solution utilizing activation sparsification and the SENECA neuromorphic processor.

Main Methods:

Developed a sparsification-aware training method to achieve low activation/spike density (∼5%) for both ANN and SNN models.
Utilized the event-driven SENECA neuromorphic processor, designed to exploit sparsity in both ANN activations and SNN spikes for accelerated inference.
Conducted hardware-in-loop experiments to measure average time and energy consumption for both network types.

Main Results:

The SNN consumed 44.9ms and 927.0μJ, representing 62.5% and 75.2% of the ANN's consumption, respectively.
SNNs exhibited significantly lower pixel-wise spike density (43.5%) compared to ANNs (66.5%).
The efficiency of SNNs was attributed to reduced memory access operations for neuron states due to lower spike density.

Conclusions:

SNNs offer a demonstrably more efficient solution for event-based optical flow compared to ANNs.
The proposed sparsification techniques and the SENECA processor effectively enhance the efficiency of both SNN and ANN inference.
Reduced memory access requirements stemming from lower spike density are key to the superior energy efficiency of SNNs in this application.