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

Classifying Matter by Composition03:35

Classifying Matter by Composition

90.4K
Matter: Pure Substances and Mixtures
According to its composition, the matter can be classified into two broad categories — pure substances and mixtures. 
A pure substance is a form of matter that has a constant composition throughout with uniform properties. For example, any sample of sucrose has the same composition and same physical properties, such as melting point, color, and sweetness, regardless of the source from which it is isolated. 
A mixture is composed of two or...
90.4K
Convolution Properties II01:17

Convolution Properties II

586
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...
586
Classifying Matter by State02:49

Classifying Matter by State

103.3K
Chemistry is the study of matter and the changes it undergoes. Matter is anything that has mass and occupies space. Matter is all around us; the air, water, soil, mountains, even our bodies are all examples of matter. Matter is divided into three states — solid, liquid, and gas — that are commonly found on earth. The fourth state of matter, plasma, occurs naturally in the interiors of stars. 
103.3K
Global Climate Change01:50

Global Climate Change

28.9K
Throughout its ~4.5 billion year history, the Earth has experienced periods of warming and cooling. However, the current drastic increase in global temperatures is well outside of the Earth’s cyclic norms, and evidence for human-caused global climate change is compelling. Paleoclimatology, the study of ancient climate conditions, provides ample evidence for human-caused global climate change by comparing recent conditions with those in the past.
28.9K
Convolution Properties I01:20

Convolution Properties I

595
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:
595
Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K

You might also read

Related Articles

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

Sort by
Same author

Triglyceride levels and all-cause mortality in patients with left main coronary artery disease undergoing percutaneous coronary intervention.

Frontiers in cardiovascular medicine·2026
Same author

Hierarchical abstraction drives human-like 3-D shape processing in deep learning models.

PLoS computational biology·2026
Same author

Threat discrimination of real-world social interactions in schizotypal traits.

Psychonomic bulletin & review·2026
Same author

Network structure shapes consensus dynamics through individual decisions.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Dual Carbon Modification and Pore Structure Regulation of CuS/FeS<sub>2</sub> Bimetallic Sulfides via Multifunctional Additives toward High-Rate and Durable Sodium Storage.

Inorganic chemistry·2025
Same author

Enhancing visuospatial mapping in relational category learning.

Journal of experimental psychology. Learning, memory, and cognition·2025
Same journal

DeepMethylation: A deep learning framework for tissue-specific DNA methylation prediction and functional variant annotation.

PLoS computational biology·2026
Same journal

Redefining and estimating the early-phase reproduction ratio for epidemic outbreaks in spatially structured populations.

PLoS computational biology·2026
Same journal

Optimized phenotype definitions boost GWAS power.

PLoS computational biology·2026
Same journal

Detection, communication, and individual identification with deep audio embeddings: A case study with North Atlantic right whales.

PLoS computational biology·2026
Same journal

Exploring the structural lexicon of the Proteome via Metric Geometry.

PLoS computational biology·2026
Same journal

Linking retinal sampling in neural encoding models to temporal profiles of visual processing in humans.

PLoS computational biology·2026
See all related articles

Related Experiment Video

Updated: Feb 1, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

1.1K

Deep convolutional networks do not classify based on global object shape.

Nicholas Baker1, Hongjing Lu1, Gennady Erlikhman2

  • 1Department of Psychology, University of California, Los Angeles, Los Angeles, California, United States of America.

Plos Computational Biology
|December 12, 2018
PubMed
Summary
This summary is machine-generated.

Deep convolutional neural networks (DCNNs) can recognize objects using local shape cues but lack global shape understanding, unlike human vision. This suggests DCNNs process visual information differently than humans.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.8K

Related Experiment Videos

Last Updated: Feb 1, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

1.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.8K

Area of Science:

  • Computer Vision
  • Cognitive Science
  • Artificial Intelligence

Background:

  • Deep convolutional neural networks (DCNNs) demonstrate high performance in object classification.
  • Biological vision relies heavily on shape for object recognition.
  • The operational similarity between DCNNs and human vision remains an open question.

Purpose of the Study:

  • To investigate the role of shape information in DCNN object recognition.
  • To compare DCNN shape processing with human visual perception.

Main Methods:

  • DCNNs were trained for object recognition.
  • Experiments involved presenting DCNNs with object silhouettes, textures, outlines, and manipulated shapes (global vs. local features).
  • Performance was compared to human accuracy under similar conditions.

Main Results:

  • DCNNs showed limited use of shape for animal classification but some for artifacts.
  • DCNNs struggled with outlines and glass figurines but could classify some silhouettes.
  • DCNNs classified objects with disrupted global shape similarly to normal shapes.
  • DCNNs failed to classify objects with altered local contours, unlike humans.

Conclusions:

  • DCNNs utilize local shape features (edge relations) but do not process global object shapes.
  • DCNNs' object recognition mechanisms differ significantly from human visual processing regarding shape information.