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

Acid-Base Titration Curves02:23

Acid-Base Titration Curves

141.0K
A titration curve is a plot of some solution property versus the amount of added titrant. For acid-base titrations, solution pH is a useful property to monitor because it varies predictably with the solution composition and, therefore, may be used to monitor the titration’s progress and detect its endpoint. Acid-base titration can be performed with a strong acid and a strong base, a strong acid and a weak base, or a strong base and a weak acid.
For a titration carried out for 25.00 mL of...
141.0K
Protein Networks02:26

Protein Networks

4.5K
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,...
4.5K
Linear time-invariant Systems01:23

Linear time-invariant Systems

899
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
899
Fixed Action Patterns01:06

Fixed Action Patterns

17.6K
A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.
17.6K
Mechanism of Breathing I: Inspiration01:30

Mechanism of Breathing I: Inspiration

3.1K
Introduction to Inspiration: The Respiratory System in Action
The respiratory system, an essential network for breathing, comprises the conducting and respiratory zones, each playing a crucial role in the overall process of respiration. Let us explore the detailed mechanism of inspiration, or inhalation, which is the first phase of the respiratory cycle.
Pathway of Air during Inspiration
During inspiration, air enters our body through the nose or mouth and moves through the conducting zone,...
3.1K
Network Covalent Solids02:18

Network Covalent Solids

16.1K
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...
16.1K

You might also read

Related Articles

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

Sort by
Same author

Nested Grover's Algorithm for Tree Search.

Entropy (Basel, Switzerland)·2026
Same author

Multilevel Data Representation for Training Deep Helmholtz Machines.

Neural computation·2025
Same author

Quantum Machine Learning-Quo Vadis?

Entropy (Basel, Switzerland)·2024
Same author

Can a Hebbian-like learning rule be avoiding the curse of dimensionality in sparse distributed data?

Biological cybernetics·2024
Same author

Promoting the Shift From Pixel-Level Correlations to Object Semantics Learning by Rethinking Computer Vision Benchmark Data Sets.

Neural computation·2024
Same author

Competitive learning to generate sparse representations for associative memory.

Neural networks : the official journal of the International Neural Network Society·2023

Related Experiment Video

Updated: Jan 28, 2026

Origami Inspired Self-assembly of Patterned and Reconfigurable Particles
12:33

Origami Inspired Self-assembly of Patterned and Reconfigurable Particles

Published on: February 4, 2013

22.2K

Attention Inspired Network: Steep learning curve in an invariant pattern recognition model.

Luis Sa-Couto1, Andreas Wichert1

  • 1Department of Computer Science and Engineering, INESC-ID & Instituto Superior Técnico, University of Lisbon, Av. Prof. Dr. Aníbal Cavaco Silva, 2744-016 Porto Salvo, Portugal.

Neural Networks : the Official Journal of the International Neural Network Society
|March 12, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning model inspired by the visual cortex for invariant pattern recognition. The model achieves high accuracy with fewer training examples by enhancing invariance without significant information loss.

Keywords:
Deep learningHubel Wiesel’s hypothesisInvariant pattern recognitionSelective attentionSteep learning

More Related Videos

Novel Object Recognition Test for the Investigation of Learning and Memory in Mice
08:52

Novel Object Recognition Test for the Investigation of Learning and Memory in Mice

Published on: August 30, 2017

77.3K
Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis
08:46

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis

Published on: September 16, 2014

8.2K

Related Experiment Videos

Last Updated: Jan 28, 2026

Origami Inspired Self-assembly of Patterned and Reconfigurable Particles
12:33

Origami Inspired Self-assembly of Patterned and Reconfigurable Particles

Published on: February 4, 2013

22.2K
Novel Object Recognition Test for the Investigation of Learning and Memory in Mice
08:52

Novel Object Recognition Test for the Investigation of Learning and Memory in Mice

Published on: August 30, 2017

77.3K
Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis
08:46

Electronic Tongue Generating Continuous Recognition Patterns for Protein Analysis

Published on: September 16, 2014

8.2K

Area of Science:

  • Computer Vision
  • Neuroscience
  • Deep Learning

Background:

  • Traditional deep models for invariant pattern recognition, inspired by low visual cortex areas, struggle with large variations due to information loss during subsampling.
  • Existing models often rely on powerful, data-hungry classifiers to compensate for limited invariance, hindering efficiency.

Purpose of the Study:

  • To develop a more effective invariant pattern recognition model by incorporating insights from higher visual cortex areas.
  • To enhance invariance capabilities without sacrificing critical information, thereby reducing reliance on complex classifiers.

Main Methods:

  • The proposed model integrates an object-centered step alongside the traditional retinotopic step, inspired by higher visual cortex functions.
  • This approach aims to increase invariance to transformations while preserving more information compared to standard subsampling techniques.
  • A simple classification mechanism based on selective attention is employed, reducing the need for a complex classifier.

Main Results:

  • The model demonstrates improved accuracy on invariant pattern recognition tasks using the MNIST and ETL-1 datasets.
  • Significantly fewer training examples are required to achieve high performance.
  • Achieved 100% accuracy on the MNIST test set using just over 10% of the training data.

Conclusions:

  • The novel model effectively enhances invariance without critical information loss, outperforming traditional methods.
  • Incorporating higher visual cortex principles leads to more efficient and data-frugal invariant pattern recognition systems.
  • The selective attention-based classification mechanism proves viable for models with enhanced intrinsic invariance.