Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

393
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...
393
Convolution Properties I01:20

Convolution Properties I

232
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:
232
Convolution Properties II01:17

Convolution Properties II

278
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...
278
Reducing Line Loss01:18

Reducing Line Loss

193
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...
193
Downsampling01:20

Downsampling

250
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
250
Vector Operations01:20

Vector Operations

1.5K
Vectors are physical quantities that have both magnitude and direction. The vector operations include addition, subtraction, and scalar multiplication.
A vector multiplied by a scalar value is called scalar multiplication. The result obtained is a new vector with a different magnitude. If the scalar is positive, the direction of the vector remains the same, but if it is negative, the direction of the vector is reversed. For example, the product of the mass and velocity yields the momentum.
1.5K

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

AlInAs step-graded buffer for reducing dark current in InAs based photodetector.

Optics express·2025
Same author

On-Off Scheduling for Electric Vehicle Charging in Two-Links Charging Stations Using Binary Optimization Approaches.

Sensors (Basel, Switzerland)·2021
Same author

Classification of Copper Minerals by Handheld Laser-Induced Breakdown Spectroscopy and Nonnegative Tensor Factorisation.

Sensors (Basel, Switzerland)·2020
Same author

Recognition of Pharmacological Bi-Heterocyclic Compounds by Using Terahertz Time Domain Spectroscopy and Chemometrics.

Sensors (Basel, Switzerland)·2019
Same author

Improved Convolutive and Under-Determined Blind Audio Source Separation with MRF Smoothing.

Cognitive computation·2013
Same author

Symmetric nonnegative matrix factorization: algorithms and applications to probabilistic clustering.

IEEE transactions on neural networks·2011
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

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

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

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

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Sep 9, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.6K

Descomposición de anillo tensorial directo de almacenamiento reducido para la compresión de redes neuronales

Mateusz Gabor1, Rafał Zdunek1

  • 1Faculty of Electronics, Photonics, and Microsystems, Wroclaw University of Science and Technology, Wybrzeze Wyspianskiego 27, Wroclaw, 50-370, Poland.

Neural networks : the official journal of the International Neural Network Society
|September 4, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Este estudio introduce un nuevo método de bajo rango para comprimir las redes neuronales convolucionales (CNNs) utilizando la descomposición de anillo tensorial directo de almacenamiento reducido (RSDTR). RSDTR reduce significativamente el tamaño y la computación del modelo mientras mantiene una alta precisión de clasificación de imágenes.

Palabras clave:
Redes neuronales convolucionalesReducción de la compresión de almacenamiento de rango bajoDescomposición del anillo tensor

Más Videos Relacionados

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

491

Videos de Experimentos Relacionados

Last Updated: Sep 9, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

491

Área de la Ciencia:

  • Visión por computadora
  • Aprendizaje automático
  • Optimización del aprendizaje profundo

Sus antecedentes:

  • Las redes neuronales convolucionales (CNN) son esenciales para tareas de visión por computadora como la clasificación de imágenes.
  • La compresión del modelo es crucial para mejorar la eficiencia de la CNN en términos de almacenamiento y computación.
  • Los métodos de aproximación de bajo rango ofrecen una vía prometedora para la compresión de CNN mediante la descomposición de núcleos grandes.

Objetivo del estudio:

  • Proponer un nuevo método de bajo rango para la compresión de la CNN.
  • Aprovechar la descomposición de anillo tensorial directo de almacenamiento reducido (RSDTR) para una aproximación eficiente del núcleo.
  • Evaluar la eficacia de RSDTR en el logro de altas tasas de compresión y la preservación de la precisión.

Principales métodos:

  • Desarrolló una nueva técnica de compresión de CNN de bajo rango basada en RSDTR.
  • Implementado RSDTR para aproximar núcleos convolucionales, reduciendo el parámetro y la complejidad de FLOPS.
  • Realizó experimentos con conjuntos de datos CIFAR-10 e ImageNet para evaluar el rendimiento.

Principales resultados:

  • El método RSDTR propuesto logró parámetros significativos y tasas de compresión FLOPS.
  • RSDTR demostró una mayor flexibilidad de permutación en modo circular en comparación con los métodos existentes.
  • Las redes comprimidas que utilizan RSDTR mantienen una precisión de clasificación competitiva.

Conclusiones:

  • RSDTR es un método eficaz para comprimir las CNN.
  • El enfoque ofrece una compensación favorable entre la eficiencia de compresión y el rendimiento de clasificación.
  • RSDTR supera a otras técnicas de compresión CNN de última generación.