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

You might also read

Related Articles

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

Sort by

Same author

Cellular psychology: relating cognition to context-sensitive pyramidal cells.

Trends in cognitive sciences·2024

Same author

Shape-Texture Debiased Training for Robust Template Matching.

Sensors (Basel, Switzerland)·2022

Same author

Distinguishing theory from implementation in predictive coding accounts of brain function.

The Behavioral and brain sciences·2013

Same author

Image segmentation using a sparse coding model of cortical area V1.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2012

Same author

A model of partial reference frame transforms through pooling of gain-modulated responses.

Cerebral cortex (New York, N.Y. : 1991)·2012

Same author

Multiplicative gain modulation arises through unsupervised learning in a predictive coding model of cortical function.

Neural computation·2011

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Comprehensive assessment methods are key to progress in deep learning.

Michael W Spratling¹

¹Department of Informatics, King's College London, London, UK michael.spratling@kcl.ac.ukhttps://nms.kcl.ac.uk/michael.spratling/.

The Behavioral and Brain Sciences

|December 6, 2023

Summary

This summary is machine-generated.

This study agrees that deep neural network (DNN) vision models have assessment and model deficits. It proposes alternative methods to address these limitations in artificial intelligence vision research.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 9, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Current deep neural network (DNN) models for vision face significant challenges.
Deficiencies exist in both the assessment methodologies and the inherent capabilities of these DNN models.

Purpose of the Study:

To address the limitations in current deep neural network (DNN) models of vision.
To propose alternative strategies for improving DNN vision model assessment and performance.

Main Methods:

Critical analysis of existing DNN vision model assessment techniques.
Development of novel approaches to evaluate and enhance DNN vision model capabilities.

Main Results:

Identified specific deficits in current DNN vision model evaluation.
Proposed a distinct set of solutions differing from previously suggested methods.

Conclusions:

The current state of DNN vision models requires significant improvement.
Alternative methodologies are crucial for advancing the field of artificial intelligence in vision.