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

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...

Improving Translational Accuracy

Improving Translational Accuracy

Associative Learning

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

Accuracy, limits, and approximation

Accuracy, limits, and approximation

Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...

Introduction to Learning

Introduction to Learning

Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...

You might also read

Related Articles

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

Sort by

Same author

The Critical Period Microbiota Shape Brain Plasticity.

bioRxiv : the preprint server for biology·2026

Same author

Evaluating the Intelligence of large language models: A comparative study using verbal and visual IQ tests.

Computers in human behavior. Artificial humans·2026

Same author

The nBAF complex subunit CREST/SS18L1 regulates hippocampal memory processes via tyrosine 397 and histone acetyltransferase CBP.

Cell reports·2026

Same author

Circadian reprogramming by timed sodium intake reveals transcriptional pathways of daily salt handling in the colon.

Science advances·2026

Same author

Chronic intermittent hypoxia reshapes circadian metabolic architecture in a model of sleep apnea.

Science advances·2026

Same author

A Dataset of Plausible Proton Transfer Steps for Arrow-Pushing Mechanisms.

Scientific data·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 Videos

SPLASH: Learnable activation functions for improving accuracy and adversarial robustness.

Mohammadamin Tavakoli¹, Forest Agostinelli², Pierre Baldi¹

¹Department of Computer Science, University of California, Irvine, United States of America.

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

|March 20, 2021

Summary

This summary is machine-generated.

We introduce SPLASH units, a novel activation function that enhances deep neural network accuracy and robustness against adversarial attacks. These units offer superior performance across various datasets and architectures, improving model security.

Keywords:

Accuracy Activation Adversarial Neural networks Robustness

Related Experiment Videos

Area of Science:

Deep Learning
Neural Network Architectures
Activation Functions

Background:

Activation functions are crucial components of deep neural networks, influencing model performance and learning capabilities.
Existing activation functions like ReLU and its variants have limitations in balancing accuracy and robustness.
Adversarial attacks pose a significant threat to the reliability of deep neural networks.

Purpose of the Study:

Introduce SPLASH units, a new class of learnable activation functions.
Evaluate the impact of SPLASH units on deep neural network accuracy and robustness.
Compare SPLASH units against existing activation functions across diverse datasets and architectures.

Main Methods:

Developed SPLASH units with specific properties: continuous, grounded (f(0)=0), symmetric hinges, and fixed hinge locations derived from data.
Implemented and tested SPLASH units in various neural network architectures (LeNet5, All-CNN, ResNet-20, Network-in-Network).
Conducted experiments on MNIST, CIFAR-10, and CIFAR-100 datasets, evaluating performance against nine other activation functions.
Assessed robustness against black-box and white-box adversarial attacks.

Main Results:

SPLASH units demonstrated superior performance compared to nine other activation functions across three datasets and four architectures.
Models utilizing SPLASH units showed significantly increased robustness to adversarial attacks, with improvements up to 31% compared to ReLU.
The effectiveness of SPLASH units was further validated on larger architectures and complex datasets like ImageNet.

Conclusions:

SPLASH units represent a promising advancement in activation function design for deep learning.
Their ability to simultaneously enhance accuracy and adversarial robustness offers a significant benefit for practical deep learning applications.
SPLASH units provide a simple yet effective method to improve the security and reliability of neural networks.