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

Protein Networks02:26

Protein Networks

4.6K
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,...
4.6K
Network Covalent Solids02:18

Network Covalent Solids

16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
Relative Risk01:12

Relative Risk

2.2K
Relative risk (RR) is a statistical measure commonly used in epidemiology to compare the likelihood of a particular event occurring between two groups. This metric is important for evaluating the relationship between exposure to a specific risk factor and the probability of a particular outcome. It plays a crucial role in medical research, public health studies, and risk assessment. Relative risk quantifies how much more (or less) likely an event is to occur in an exposed group compared to an...
2.2K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.6K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K
Relative Velocity in One Dimension01:10

Relative Velocity in One Dimension

10.7K
The understanding of the concept of reference frames is essential to discuss relative motion in one or more dimensions. When we say that an object has a certain velocity, we must state the velocity with respect to a given reference frame. In most examples, this reference frame has been Earth. For instance, if a statement reads that a person is sitting in a train moving at 10 m/s east, then it implies that the person on the train is moving relative to the surface of Earth at this velocity,...
10.7K
Thermal Strain01:19

Thermal Strain

2.9K
Thermal strain is a concept that arises when we consider how temperature changes affect structures. Unlike the conventional assumption that structures remain constant under load, real-world scenarios often involve temperature fluctuations that can significantly impact these structures. Consider a homogeneous rod with a uniform cross-section resting freely on a flat horizontal surface. If the rod's temperature increases, the rod elongates. This elongation is proportional to the temperature...
2.9K

You might also read

Related Articles

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

Sort by
Same author

Perilesional neuromodulation replaces lost sensorimotor function in persons with spinal cord injury.

Nature biomedical engineering·2026
Same author

Topological control of spontaneous failure in active nematic solids.

Nature materials·2026
Same author

An active electronic, high-density epidural paddle array for chronic spinal cord neuromodulation.

bioRxiv : the preprint server for biology·2024
Same author

Monkeys engage in visual simulation to solve complex problems.

bioRxiv : the preprint server for biology·2024
Same author

Multimodal sensory control of motor performance by glycinergic interneurons of the mouse spinal cord deep dorsal horn.

Neuron·2024
Same author

Fixing the problems of deep neural networks will require better training data and learning algorithms.

The Behavioral and brain sciences·2023
Same journal

Equity considerations in COVID-19 vaccine allocation modelling: a methodological study.

Interface focus·2025
Same journal

Ethical considerations in infectious disease modelling for public health policy: the case of school closures.

Interface focus·2025
Same journal

Why population heterogeneity matters for modelling infectious diseases.

Interface focus·2025
Same journal

Improving modelling for epidemic response: a progress update from a community of UK infectious disease modellers.

Interface focus·2025
Same journal

Optimization of school closures during an Omicron epidemic in Hong Kong: a modelling study.

Interface focus·2025
Same journal

Impact of opinion dynamics on recurrent pandemic waves: balancing risk aversion and peer pressure.

Interface focus·2025
See all related articles

Related Experiment Video

Updated: Feb 8, 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

Not-So-CLEVR: learning same-different relations strains feedforward neural networks.

Junkyung Kim1, Matthew Ricci1, Thomas Serre1

  • 1Department of Cognitive, Linguistic & Psychological Sciences, Carney Institute for Brain Science, Brown University, Providence, RI 02912, USA.

Interface Focus
|June 29, 2018
PubMed
Summary
This summary is machine-generated.

Deep learning models, like feedforward neural networks, excel at image recognition but struggle with abstract visual relations. Introducing perceptual grouping significantly improves their ability to learn same-different tasks, highlighting the importance of feedback mechanisms.

Keywords:
convolutional neural networksdeep learningperceptual groupingvisual attentionvisual relationsworking memory

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
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K

Related Experiment Videos

Last Updated: Feb 8, 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
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K

Area of Science:

  • Computer Science
  • Neuroscience
  • Cognitive Science

Background:

  • Deep learning, particularly convolutional neural networks, has achieved human-level performance in visual recognition tasks.
  • However, feedforward neural networks exhibit limitations in learning abstract visual relations, unlike biological systems.

Purpose of the Study:

  • To investigate the capability of feedforward neural networks in learning abstract visual relations.
  • To identify the specific challenges faced by these networks in recognizing same-different visual relationships.
  • To explore the role of perceptual grouping in enhancing the learning of visual relations.

Main Methods:

  • Systematic evaluation of feedforward neural network performance on various visual relation tasks.
  • Analysis of network failures in learning same-different relations under stimulus variability.
  • Comparison of network performance with and without perceptually grouped stimuli.

Main Results:

  • Feedforward neural networks struggle to learn abstract visual relations, especially same-different tasks.
  • Network performance degrades when stimulus variability hinders rote memorization.
  • Perceptual grouping of stimuli dramatically improves the network's ability to learn same-different visual relations.

Conclusions:

  • Abstract visual reasoning in biological systems may rely on feedback mechanisms like attention, working memory, and perceptual grouping.
  • These mechanisms are crucial for overcoming limitations in feedforward neural network architectures for complex visual tasks.
  • Future research should focus on incorporating feedback loops to enhance artificial visual intelligence.