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

Woodward–Hoffmann Selection Rules and Microscopic Reversibility01:34

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

2.2K
Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...
2.2K
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model01:13

Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model

427
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
427
Reversible and Irreversible Processes01:14

Reversible and Irreversible Processes

4.3K
The thermodynamic processes can be classified into reversible and irreversible processes. The processes that can be restored to their initial state are called reversible processes. It is only possible if the process is in quasi-static equilibrium, i.e., it takes place in infinitesimally small steps, and the system remains at equilibrium However, these are ideal processes and do not occur naturally. An ideal system undergoing a reversible process is always in thermodynamic equilibrium within...
4.3K
End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

1.5K
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
1.5K
Entropy Change in Reversible Processes01:10

Entropy Change in Reversible Processes

2.4K
In the Carnot engine, which achieves the maximum efficiency between two reservoirs of fixed temperatures, the total change in entropy is zero. The observation can be generalized by considering any reversible cyclic process consisting of many Carnot cycles. Thus, it can be stated that the total entropy change of any ideal reversible cycle is zero.
The statement can be further generalized to prove that entropy is a state function. Take a cyclic process between any two points on a p-V diagram.
2.4K

You might also read

Related Articles

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

Sort by
Same author

Machine learning assisted multi-criteria decision-making approaches for site selection: A systematic review.

MethodsX·2026
Same author

HierarchicalNets for multi level hierarchical classification of yoga poses.

Scientific reports·2026
Same author

Strategies at a glance: A comparative analysis of training techniques for optimizing early-exit deep neural networks.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Improving Object Detection in High-Altitude Infrared Thermal Images Using Magnitude-Based Pruning and Non-Maximum Suppression.

Journal of imaging·2025
Same author

Four Transformer-Based Deep Learning Classifiers Embedded with an Attention U-Net-Based Lung Segmenter and Layer-Wise Relevance Propagation-Based Heatmaps for COVID-19 X-ray Scans.

Diagnostics (Basel, Switzerland)·2024
Same author

A comparison of deep transfer learning backbone architecture techniques for printed text detection of different font styles from unstructured documents.

PeerJ. Computer science·2024
Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026
Same journal

Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

IEEE transactions on neural networks and learning systems·2026
Same journal

cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

IEEE transactions on neural networks and learning systems·2026
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: May 2, 2026

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

1.7K

XAI-Exit: Interpretability-Driven Dynamic Early Exits for Efficient and Transparent DNN Inference.

Haseena Rahmath P, Ajith Abraham, Kuldeep Chaurasia

    IEEE Transactions on Neural Networks and Learning Systems
    |April 30, 2026
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces XAI-Exit, an early exit framework for deep neural networks (DNNs). It enhances efficiency and transparency, making AI decisions more interpretable for critical applications.

    Related Experiment Videos

    Last Updated: May 2, 2026

    Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
    10:44

    Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

    Published on: December 7, 2021

    1.7K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computer Vision

    Background:

    • Deep neural networks (DNNs) offer high performance but suffer from significant computational costs and lack of transparency.
    • Early exit strategies in DNNs improve efficiency but often compromise interpretability, hindering trust in AI systems.
    • Resource-constrained and critical AI applications demand models that are both efficient and transparent.

    Purpose of the Study:

    • To present XAI-Exit, a novel framework that optimizes both efficiency and transparency in early exit DNNs.
    • To develop a method for dynamically predicting the optimal exit point in a DNN.
    • To ensure that the decision-making process of early exit DNNs is interpretable.

    Main Methods:

    • XAI-Exit utilizes ExitDecisionNet (EDN), a recurrent neural network (RNN) trained with a curriculum strategy focusing on confidence, interpretability, and stability.
    • A skip mechanism is incorporated to minimize redundant computations within the network.
    • Transparency is achieved through exit attribution maps (EAMs) and integration with established Explainable AI (XAI) techniques like Integrated Gradients (IGs), SmoothGrad, Grad-CAM++, and LRP.

    Main Results:

    • XAI-Exit demonstrates improved computational efficiency without compromising predictive accuracy across various DNN architectures (MobileNetV3, ResNet18, MSDNet) and datasets (CIFAR-10, CIFAR-100, ImageNet).
    • The framework successfully provides interpretable exit decisions by aggregating feature attributions.
    • The proposed method ensures that the choice of exit point is transparent and understandable.

    Conclusions:

    • XAI-Exit offers a viable solution for deploying efficient and transparent DNNs in real-world, high-stakes scenarios.
    • The joint optimization of efficiency and interpretability is crucial for building trustworthy AI systems.
    • This framework advances the practical applicability of early exit strategies in AI.