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

Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

904
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
904
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

145
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
145
What are Estimates?01:06

What are Estimates?

6.8K
It isn't easy to measure a parameter such as the mean height or the mean weight of a population. So, we draw samples from the population and calculate the mean height or mean weight of the individuals in the sample. This sample data acts as a representative measure of the population parameter. These sample statistics are known as estimates. 
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
6.8K
Estimation of the Physical Quantities01:05

Estimation of the Physical Quantities

6.6K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
6.6K
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

174
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
174
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

204
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
204

You might also read

Related Articles

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

Sort by
Same author

Decision-level processes in rapid numerosity estimation.

Cognition·2026
Same author

Advancing spatio-temporal processing through adaptation in spiking neural networks.

Nature communications·2025
Same author

Neural network-based reconstruction of steady-state temperature systems with unknown material composition.

Scientific reports·2024
Same author

COSMIC: the Catalogue Of Somatic Mutations In Cancer.

Nucleic acids research·2018
Same author

Publisher Correction: Studying light-harvesting models with superconducting circuits.

Nature communications·2018
Same author

Studying light-harvesting models with superconducting circuits.

Nature communications·2018
Same journal

Evidence for abstract spatial concept learning in young animals.

Cognition·2026
Same journal

Blurred lines or clear boundaries? Synchrony and social dominance shape domain-specific self-other processing.

Cognition·2026
Same journal

Knowability predicts curiosity and learning.

Cognition·2026
Same journal

Throwing good effort after bad: Evidence for a sunk-cost effect in cognitive effort-based decision-making.

Cognition·2026
Same journal

Cross-linguistic differences in incremental planning under uncertainty.

Cognition·2026
Same journal

Sensory attenuation scales with the strength of action-outcome coupling: A psychophysical study.

Cognition·2026
See all related articles

Related Experiment Video

Updated: Oct 31, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Learning exact enumeration and approximate estimation in deep neural network models.

Celestino Creatore1, Silvester Sabathiel2, Trygve Solstad1

  • 1Department of Teacher Education, Faculty of Social and Educational Sciences, NTNU-Norwegian University of Science and Technology, Norway.

Cognition
|June 28, 2021
PubMed
Summary
This summary is machine-generated.

Neural networks can learn exact numerosity using different mechanisms. Deep Belief Networks (DBNs) use summation units for approximate number systems, while Hierarchical Convolutional Neural Networks (HCNNs) use numerosity codes for exact recognition.

Keywords:
Approximate numberComputational modellingDeep neural networksExact numberNumber senseRepresentations

More Related Videos

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

729

Related Experiment Videos

Last Updated: Oct 31, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
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

729

Area of Science:

  • Cognitive Science
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Approximate number discrimination emerges in Deep Belief Networks (DBNs) and Hierarchical Convolutional Neural Networks (HCNNs).
  • Investigated whether these neural network architectures can also learn exact numerosity recognition.

Purpose of the Study:

  • To determine if DBNs and HCNNs can learn exact numerosity.
  • To analyze the neural mechanisms underlying exact numerosity recognition in these models.

Main Methods:

  • Utilized two hierarchical neural network models: a generative Deep Belief Network (DBN) and a Hierarchical Convolutional Neural Network (HCNN).
  • Trained HCNNs on natural object classification.
  • Analyzed the response specificity of units in the last hidden layer of both networks.

Main Results:

  • DBNs developed 'summation units' enabling approximate number system behavior.
  • HCNNs developed units encoding a 'numerosity code' for near-perfect exact numerosity classification.
  • Performance differences were linked to the specificity of unit responses in the hidden layer.

Conclusions:

  • Parallel pattern-recognition mechanisms may underlie both exact and approximate number concepts.
  • These mechanisms could contribute to learning symbolic numbers and arithmetic.
  • Neural network architectures offer insights into the cognitive processes of numerical representation.