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

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:

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...

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...

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...

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...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by

Same author

Fusion Attention for Action Recognition: Integrating Sparse-Dense and Global Attention for Video Action Recognition.

Sensors (Basel, Switzerland)·2024

Same author

Adjacent Image Augmentation and Its Framework for Self-Supervised Learning in Anomaly Detection.

Sensors (Basel, Switzerland)·2024

Same author

A web-based care assistant for caregivers of the elderly: Development and pilot study.

Digital health·2023

Same author

LMGAN: Linguistically Informed Semi-Supervised GAN with Multiple Generators.

Sensors (Basel, Switzerland)·2022

Same author

UAT: Universal Attention Transformer for Video Captioning.

Sensors (Basel, Switzerland)·2022

Same author

Enhancing Targeted Minority Class Prediction in Sentence-Level Relation Extraction.

Sensors (Basel, Switzerland)·2022

Search research articles

Related Experiment Video

Updated: Oct 30, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

HyAdamC: A New Adam-Based Hybrid Optimization Algorithm for Convolution Neural Networks.

Kyung-Soo Kim¹, Yong-Suk Choi²

¹Center for Computational Social Science, Hanyang University, Seoul 04763, Korea.

Sensors (Basel, Switzerland)

|July 2, 2021

Summary

This summary is machine-generated.

This study introduces HyAdamC, a novel hybrid optimization method for training deep learning models like Convolutional Neural Networks (CNNs). HyAdamC enhances training stability and accuracy in image processing tasks.

Keywords:

adam optimization convolution neural networks deep learning first-order optimization gradient descent image classification optimization

Related Experiment Videos

Last Updated: Oct 30, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Deep learning models, especially Convolutional Neural Networks (CNNs), excel in image processing tasks.
Traditional optimizers struggle with training deep and complex CNNs effectively.
Advanced optimization methods are crucial for robust CNN training.

Purpose of the Study:

To propose HyAdamC, a new Adam-based hybrid optimization method for efficient CNN training.
To enhance the stability and robustness of optimization for deep learning models.
To improve training performance in image classification and segmentation tasks.

Main Methods:

Developed HyAdamC, integrating three novel velocity control functions for dynamic search strength adjustment.
Implemented an adaptive coefficient computation method to mitigate outlier gradient impact on search direction.
Combined these components into a unified hybrid optimization strategy.

Main Results:

HyAdamC demonstrated notable test accuracies across various CNN models.
The method exhibited significantly stable and robust optimization capabilities.
Effective application in both image classification and image segmentation tasks was confirmed.

Conclusions:

HyAdamC offers a superior optimization solution for training CNNs compared to traditional methods.
The proposed method enhances both performance accuracy and training stability.
HyAdamC shows broad applicability in computer vision tasks.