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

Neural Circuits01:25

Neural Circuits

2.1K
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...
2.1K
Neural Regulation01:37

Neural Regulation

41.6K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
41.6K
Comparison between RL and RC circuits01:24

Comparison between RL and RC circuits

5.3K
An RC circuit consists of resistance and capacitance, while in an RL circuit, capacitance is replaced by an inductor. RL and RC circuits are first-order differential circuits that store energy. An RC circuit stores energy in the electric field, while an RL circuit stores energy in the magnetic field. When connected to a battery, an RC circuit charges the capacitor, causing the current to decrease from maximum to zero upon being fully charged. This increases the voltage across the capacitor from...
5.3K
Reliability and Validity01:29

Reliability and Validity

13.4K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
13.4K

You might also read

Related Articles

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

Sort by
Same author

Why Hearing Aids Fail and How to Solve This.

Frontiers in network physiology·2023
Same author

Exploiting deterministic features in apparently stochastic data.

Scientific reports·2022
Same author

The Analysis of Mammalian Hearing Systems Supports the Hypothesis That Criticality Favors Neuronal Information Representation but Not Computation.

Entropy (Basel, Switzerland)·2022
Same author

Financial markets' deterministic aspects modeled by a low-dimensional equation.

Scientific reports·2022
Same author

Excess Entropies Suggest the Physiology of Neurons to Be Primed for Higher-Level Computation.

Physical review letters·2021
Same author

Second-order phase transition in phytoplankton trait dynamics.

Chaos (Woodbury, N.Y.)·2020

Related Experiment Video

Updated: Nov 16, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.3K

Note on the Reliability of Biological vs. Artificial Neural Networks.

Ruedi Stoop1,2

  • 1Department of Physics, Institute of Neuroinformatics, University and ETH Zürich, Zurich, Switzerland.

Frontiers in Physiology
|March 1, 2021
PubMed
Summary
This summary is machine-generated.

Artificial neural networks struggle with novel situations unlike humans, revealing a key intelligence gap. This study analyzes fundamental examples to explain why AI fails where human intelligence succeeds in unexpected scenarios.

Keywords:
artificial vs. biological neural networksgeneralization abilityinfluence of evolutionnetwork solution reliabilitysize and structure of problem solutions

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.6K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K

Related Experiment Videos

Last Updated: Nov 16, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.3K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.6K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Machine Learning

Background:

  • Neural networks are widely applied in technology due to their generalization capabilities.
  • Generalization in artificial intelligence (AI) raises expectations for handling novel situations akin to human adaptability.
  • Current AI performance in unexpected scenarios often falls short compared to human abilities.

Purpose of the Study:

  • To investigate the limitations of artificial neural networks in handling situations outside their training data.
  • To analyze the fundamental reasons behind the performance disparity between AI and human intelligence in novel contexts.
  • To provide an initial analysis of a problem that has received limited attention.

Main Methods:

  • Utilized fundamental, simplified examples to illustrate AI limitations.
  • Focused on scenarios not encountered during the training of artificial approaches.
  • Analyzed key features contributing to the differences between human and artificial intelligence.

Main Results:

  • Artificial neural networks encounter substantial problems when faced with untrained situations.
  • The study highlights a significant deficit in AI's ability to generalize compared to human cognitive flexibility.
  • Identified key factors contributing to AI's failure in novel scenarios.

Conclusions:

  • Despite their generalization capabilities, current artificial neural networks exhibit critical weaknesses in handling unexpected situations.
  • A notable gap exists between human intelligence and AI in adapting to and successfully navigating novel environments.
  • Further research is needed to address these limitations and bridge the gap between artificial and human intelligence.