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

204
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:
204
Neural Circuits01:25

Neural Circuits

1.4K
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...
1.4K
Convolution Properties II01:17

Convolution Properties II

253
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...
253
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

324
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...
324
Directional Terms01:14

Directional Terms

8.9K
Directional terms are essential for describing the relative locations of different body structures. For instance, an anatomist might describe one band of tissue as "inferior to" another, or a physician might describe a tumor as "superficial to" a deeper body structure. These terms often use comparative terms in pairs to trace out the relative locations of one body part to another or descriptions of body tissues like the deeper ones from superficially present with reference to...
8.9K
Associative Learning01:27

Associative Learning

484
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...
484

You might also read

Related Articles

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

Sort by
Same author

Connecting the dots - recognition of artificial and natural shapes relies on representing points of high information.

Vision research·2026
Same author

Diagnostic Outcomes of Robotic Bronchoscopy in a Multidisciplinary, Multi-hospital Lung Nodule Program.

The Journal of surgical research·2026
Same author

Small Scale Dissection and Antibody Staining of Eye-Antennal and Wing Imaginal Discs from Drosophila melanogaster.

Journal of visualized experiments : JoVE·2026
Same author

Three-dimensional shape cues affect human and artificial recognition systems differently.

PloS one·2026
Same author

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

PLoS computational biology·2026
Same author

Overground gait transitions are not sharp but involve gradually changing walk-run mixtures even over long distances.

Royal Society open science·2025
Same journal

Structural impact of non-IID heterogeneity on federated behavioral anomaly detection in IoT and IoMT systems.

Frontiers in artificial intelligence·2026
Same journal

DiscoVerse: multi-agent pharmaceutical co-scientist for traceable drug discovery and reverse translation.

Frontiers in artificial intelligence·2026
Same journal

EEG-based cognition-aware task classification and scheduling using enhanced fuzzy transition modeling.

Frontiers in artificial intelligence·2026
Same journal

Autofluorescence and deep learning in early disease detection: biological foundations, clinical applications, and future directions.

Frontiers in artificial intelligence·2026
Same journal

Legal document summarization: a short review.

Frontiers in artificial intelligence·2026
Same journal

Generative AI adoption and its impact on teachers' self-efficacy and instructional confidence in Ghana.

Frontiers in artificial intelligence·2026
See all related articles

Related Experiment Video

Updated: Aug 6, 2025

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

594

Configural relations in humans and deep convolutional neural networks.

Nicholas Baker1, Patrick Garrigan2, Austin Phillips3

  • 1Department of Psychology, Loyola University Chicago, Chicago, IL, United States.

Frontiers in Artificial Intelligence
|March 20, 2023
PubMed
Summary
This summary is machine-generated.

Deep convolutional neural networks (DCNNs) struggle with relational reasoning, unlike humans. These AI models show significant limitations in understanding and generalizing concepts like sameness, enclosure, and quantity, hindering their perceptual capabilities.

Keywords:
DCNNsabstract relationsabstract representationdeep convolutional neural networksdeep learningperception of relationsshape perceptionvisual relations

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

9.3K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Related Experiment Videos

Last Updated: Aug 6, 2025

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

594
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Area of Science:

  • Cognitive Science
  • Artificial Intelligence
  • Computer Vision

Background:

  • Deep convolutional neural networks (DCNNs) are powerful tools for image recognition.
  • Previous research indicated DCNNs lack sensitivity to global object shape.
  • This study explores if DCNNs also exhibit limitations in processing object relations.

Purpose of the Study:

  • To investigate the relational processing capabilities of DCNNs (AlexNet, ResNet-50).
  • To compare DCNNs' learning and generalization of relations against human performance.
  • To identify limitations in DCNNs' abstraction and relational processing.

Main Methods:

  • Tested DCNNs on three relational tasks: same-different shape classification, object enclosure detection, and polygon side-count comparison.
  • Utilized DCNNs pre-trained on ImageNet, employing restricted and unrestricted transfer learning.
  • Compared DCNN performance with human observers on the same tasks.

Main Results:

  • DCNNs showed poor generalization for same-different shape tasks.
  • Enclosure task performance was near chance for restricted transfer learning and moderately successful for unrestricted.
  • Polygon side-count learning was successful for simple cases but failed generalization to more complex polygons.
  • Human observers demonstrated robust learning and generalization across all relational tasks.

Conclusions:

  • DCNNs possess significant limitations in abstract and relational processing compared to humans.
  • These limitations hinder DCNNs' ability to generalize relational understanding.
  • DCNNs' current architecture may not support the fundamental relational computations seen in human perception.