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

Synaptic Signaling01:12

Synaptic Signaling

79.8K
Neurons communicate at synapses, or junctions, to excite or inhibit the activity of other neurons or target cells, such as muscles. Synapses may be chemical or electrical.
79.8K
Synaptic Signaling01:09

Synaptic Signaling

6.7K
Neurons communicate at synapses, or junctions, to excite or inhibit the activity of other neurons or target cells, such as muscles. Synapses may be chemical or electrical.
Most synapses are chemical, meaning an electrical impulse or action potential spurs the release of chemical messengers called neurotransmitters. The neuron sending the signal is called the presynaptic neuron, and the neuron receiving the signal is the postsynaptic neuron.
The presynaptic neuron fires an action potential that...
6.7K
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
Uncertainty in Measurement: Accuracy and Precision03:37

Uncertainty in Measurement: Accuracy and Precision

102.7K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value. 
102.7K
Accuracy and Precision01:52

Accuracy and Precision

15.5K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.  Highly accurate...
15.5K

You might also read

Related Articles

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

Sort by
Same author

Sampling the space of solutions of an artificial neural network.

Physical review. E·2025
Same author

Bias-inducing geometries: An exactly solvable data model with fairness implications.

Physical review. E·2025
Same author

STanH : Parametric Quantization for Variable Rate Learned Image Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

Gaussian universality of perceptrons with random labels.

Physical review. E·2024
Same author

Exponential Capacity of Dense Associative Memories.

Physical review letters·2024
Same author

Information-theoretical analysis of the neural code for decoupled face representation.

PloS one·2024

Related Experiment Video

Updated: Feb 7, 2026

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

Role of Synaptic Stochasticity in Training Low-Precision Neural Networks.

Carlo Baldassi1,2,3, Federica Gerace2,4, Hilbert J Kappen5

  • 1Bocconi Institute for Data Science and Analytics, Bocconi University, Milano 20136, Italy.

Physical Review Letters
|July 14, 2018
PubMed
Summary

Neural networks with stochastic binary weights find rare, robust solutions for better generalization. This method trains discrete deep neural networks, overcoming challenges in typical solution isolation.

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

1.1K
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 7, 2026

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
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
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:

  • Computational neuroscience
  • Machine learning theory

Background:

  • Stochasticity and limited precision in synaptic weights are crucial for biological and hardware neural network models.
  • Understanding how these factors influence learning and solution properties is essential.

Purpose of the Study:

  • To investigate neural network models with stochastic binary weights.
  • To demonstrate that such models naturally favor rare, dense solution regions with desirable properties.
  • To explore training methods for discrete deep neural networks.

Main Methods:

  • Development of a neural network model with stochastic binary weights.
  • Application of a gradient descent procedure on real-valued parameters to obtain binary solutions.
  • Analytical and numerical analysis of the model's behavior.
  • Investigation of algorithmic extensions for training discrete deep neural networks.

Main Results:

  • Models with stochastic binary weights highlight exponentially rare solution regions.
  • These rare solutions exhibit robustness and good generalization performance.
  • Typical solutions are isolated and difficult to find.
  • Binary solutions for the standard perceptron problem are achievable via gradient descent.

Conclusions:

  • Stochastic binary weights offer a pathway to discovering high-quality, robust solutions in neural networks.
  • The proposed gradient descent method effectively trains models with discrete weights.
  • This approach has implications for both theoretical understanding and practical applications in discrete deep learning.