Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Convolution Properties I01:20

Convolution Properties I

296
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:
296
Convolution Properties II01:17

Convolution Properties II

335
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...
335
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

504
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...
504
Propagation of Action Potentials01:23

Propagation of Action Potentials

7.6K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
7.6K
Neural Circuits01:25

Neural Circuits

1.9K
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...
1.9K
Deconvolution01:20

Deconvolution

326
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...
326

You might also read

Related Articles

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

Sort by
Same author

Convolutional- and Deep Learning-Based Techniques for Time Series Ordinal Classification.

IEEE transactions on cybernetics·2025
Same author

Gender-Equity Model for Liver Allocation Using Artificial Intelligence (GEMA-AI) for Waiting List Liver Transplant Prioritization.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2025
Same author

Machine Learning Algorithms in Controlled Donation After Circulatory Death Under Normothermic Regional Perfusion: A Graft Survival Prediction Model.

Transplantation·2025
Same author

Deep Ordinal Classification in Forest Areas Using Light Detection and Ranging Point Clouds.

Sensors (Basel, Switzerland)·2024
Same author

Learning Ordinal-Hierarchical Constraints for Deep Learning Classifiers.

IEEE transactions on neural networks and learning systems·2024
Same author

Cluster analysis and forecasting of viruses incidence growth curves: Application to SARS-CoV-2.

Expert systems with applications·2023

Related Experiment Video

Updated: Oct 23, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

618

Activation Functions for Convolutional Neural Networks: Proposals and Experimental Study.

Victor Manuel Vargas, Pedro Antonio Gutierrez, Javier Barbero-Gomez

    IEEE Transactions on Neural Networks and Learning Systems
    |August 24, 2021
    PubMed
    Summary

    Two novel activation functions for neural networks demonstrate superior performance compared to 17 existing alternatives across diverse problems. These new functions enhance model capabilities by optimizing layer output ranges.

    More Related Videos

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
    11:18

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

    Published on: March 2, 2015

    10.5K

    Related Experiment Videos

    Last Updated: Oct 23, 2025

    Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
    06:19

    Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

    Published on: August 16, 2024

    618
    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
    11:18

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

    Published on: March 2, 2015

    10.5K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Deep Learning

    Background:

    • Activation functions are fundamental components in neural networks, influencing layer output and overall model capabilities.
    • Current deep learning models predominantly utilize a limited set of activation functions, such as ReLU.
    • The selection of activation functions significantly impacts neural network performance across various applications.

    Purpose of the Study:

    • To introduce and analyze two novel activation functions for neural networks.
    • To compare the performance of the proposed activation functions against 17 existing alternatives.
    • To evaluate the effectiveness of different activation functions on diverse machine learning problems.

    Main Methods:

    • Development of two new activation functions.
    • Comparative analysis of proposed functions with 17 existing activation functions from recent literature.
    • Empirical evaluation on six distinct datasets representing varied problem characteristics.

    Main Results:

    • The proposed activation functions outperformed commonly used alternatives in the conducted experiments.
    • Comparative analysis revealed significant performance differences across the tested activation functions.
    • The study highlights the impact of activation function choice on model performance.

    Conclusions:

    • The novel activation functions proposed in this study offer improved performance over existing methods.
    • The findings suggest that specialized activation functions can enhance neural network capabilities.
    • Further research into novel activation functions is warranted for advancing deep learning models.