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

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

Convolution: Math, Graphics, and Discrete Signals

Convolution: Math, Graphics, and Discrete Signals

In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...

Convolution Properties I

Convolution Properties I

Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:

Reducing Line Loss

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...

Convolution Properties II

Convolution Properties II

The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...

You might also read

Related Articles

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

Sort by

Same author

CDK9 degrader induces BRCAness and sensitizes castration-resistant prostate cancer to PARP inhibitor.

Theranostics·2026

Same author

Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-View Geo-Localization.

IEEE transactions on neural networks and learning systems·2026

Same author

Functionalized polymeric nanomaterials for BMP-2 delivery: recent advances toward improved bone regeneration.

Nanomedicine (London, England)·2026

Same author

Brain-Controlled Wheeled Mobile Robots: A Shared Control Framework Integrating Event-Triggered Mechanism and Deep Reinforcement Learning.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same author

Robust 3D Multi-Object Tracking via 4D mmWave Radar-Camera Fusion and Disparity-Domain Depth Recovery.

Sensors (Basel, Switzerland)·2026

Same author

A highly energy-efficient multi-core neuromorphic architecture for training deep spiking neural networks.

Nature communications·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

Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 11, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Compressing 3DCNNs based on tensor train decomposition.

Dingheng Wang¹, Guangshe Zhao¹, Guoqi Li²

¹School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China.

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

|August 18, 2020

Summary

This summary is machine-generated.

Tensor Train (TT) decomposition effectively shrinks three-dimensional convolutional neural networks (3DCNNs), reducing model size by 100x. This compression enables efficient deployment of 3DCNNs on embedded devices without sacrificing accuracy.

Keywords:

3DCNN Neural network compression Tensor train decomposition Tensorizing

Related Experiment Videos

Last Updated: Dec 11, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Computer Vision
Deep Learning
Machine Learning

Background:

Three-dimensional convolutional neural networks (3DCNNs) are effective for tasks like video and 3D point cloud recognition.
The high dimensionality of 3DCNN kernels leads to significant space complexity, hindering deployment on resource-constrained devices.
Neural network compression is crucial for miniaturizing 3DCNNs for embedded applications.

Purpose of the Study:

To investigate the efficacy of Tensor Train (TT) decomposition for compressing 3DCNN models.
To explore the selection of appropriate TT ranks for maximizing compression ratios.
To analyze the redundancy of 3D convolutional kernels and discuss future research directions.

Main Methods:

Adopted Tensor Train (TT) decomposition as an in situ training compression method for 3DCNNs.
Proposed tensorizing 3D convolutional kernels into TT format.
Conducted experiments on VIVA challenge, UCF11, UCF101, and ModelNet40 datasets.

Main Results:

Achieved compression of 3DCNN models by approximately 100 times using TT decomposition.
Demonstrated that TT decomposition can be performed without significant loss of model accuracy.
Evaluated theoretical computation complexity against practical execution time for TT convolutions.

Conclusions:

TT decomposition is a viable and effective method for compressing 3DCNNs.
The developed compression technique enables the application of 3DCNNs in various real-world scenarios with limited resources.
Further research can explore kernel redundancy and optimize TT rank selection for enhanced compression.