Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Uniform Distribution

Uniform Distribution

The uniform distribution is a continuous probability distribution of events with an equal probability of occurrence. This distribution is rectangular.Two essential properties of this distribution are The area under the rectangular shape equals 1. There is a correspondence between the probability of an event and the area under the curve.Further, the mean and standard deviation of the uniform distribution can be calculated when the lower and upper cut-offs, denoted as a and b,...

Law of Independent Assortment

Law of Independent Assortment

While Mendel’s Law of Segregation states that the two alleles for one gene are separated into different gametes, a different question of how different genes are inherited remains. For example, is the gene for tall plants inherited with the gene for green peas? Mendel asked this question by experimenting with a dihybrid cross; a cross in which both parents are homozygous for two distinct traits resulting in an F1 generation that are heterozygous for both traits.

Law of Independent Assortment

Law of Independent Assortment

While Mendel’s Law of Segregation states that the two alleles for one gene are separated into different gametes, a different question of how different genes are inherited remains. For example, is the gene for tall plants inherited with the gene for green peas? Mendel asked this question by experimenting with a dihybrid cross; a cross in which both parents are homozygous for two distinct traits resulting in an F1 generation that are heterozygous for both traits.

Probability Distributions

Probability Distributions

The probability of a random variable x is the likelihood of its occurrence. A probability distribution represents the probabilities of a random variable using a formula, graph, or table. There are two types of probability distribution– discrete probability distribution and continuous probability distribution.
A discrete probability distribution is a probability distribution of discrete random variables. It can be categorized into binomial probability distribution and Poisson probability...

Introduction to Normal Distributions

Introduction to Normal Distributions

Standardized test scores often follow a symmetric distribution that can be modeled with the normal distribution, a fundamental concept in statistics. This distribution is particularly useful for interpreting test performance fairly across populations, as it provides a mathematical framework for understanding variability and central tendency in large datasets.From Histogram to Frequency DistributionRaw test data are often displayed using histograms, where the height of each bar represents the...

Probability Laws

Probability Laws

You might also read

Related Articles

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

Sort by

Same author

Recurrent neural networks as neuro-computational models of human speech recognition.

PLoS computational biology·2025

Same author

Lexical Feedback in the Time-Invariant String Kernel (TISK) Model of Spoken Word Recognition.

Journal of cognition·2024

Same author

Rethinking Weight Decay for Efficient Neural Network Pruning.

Journal of imaging·2022

Same author

Extraction of Knowledge from the Topographic Attentive Mapping Network and its Application in Skill Analysis of Table Tennis.

Journal of human kinetics·2017

Same author

Origins of the specialization for letters and numbers in ventral occipitotemporal cortex.

Trends in cognitive sciences·2015

Same author

On the time-course of adjacent and non-adjacent transposed-letter priming.

Journal of cognitive psychology (Hove, England)·2014

Search research articles

Related Experiment Video

Updated: May 13, 2026

The (Spatial) Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

The (Spatial) Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

Published on: February 19, 2018

Learning spatial invariance with the trace rule in nonuniform distributions.

Jasmin Leveillé¹, Thomas Hannagan

¹Center for Computational Neuroscience and Neural Technology, Boston University, Boston, MA 02215, USA. jalev51@gmail.com

Neural Computation

|March 9, 2013

Summary

Trace learning rules can enable convolutional models to achieve spatial invariance in object recognition. This addresses how identical synaptic weights are learned, even with uneven data distributions, optimizing feature detection.

More Related Videos

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Related Experiment Videos

Last Updated: May 13, 2026

The (Spatial) Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

The (Spatial) Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

Published on: February 19, 2018

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Area of Science:

Computational neuroscience
Machine learning
Computer vision

Background:

Convolutional models achieve spatial invariance in object recognition via pooling operators (max or average).
This invariance relies on equal synaptic weight strengths connecting similarly tuned units to pooling units.
Learning identical weights with nonuniform data distribution is a significant challenge.

Purpose of the Study:

To investigate how trace learning rules can facilitate the learning of identical synaptic weights.
To explain previously published results on spatial invariance in neural networks.
To recommend optimal trace learning rules for invariance learning in computational models.

Main Methods:

Theoretical analysis of various trace learning rule versions.
Modeling synaptic weight learning under nonuniform data distributions.
Comparison with existing findings in computational neuroscience and machine learning.

Main Results:

Demonstrated that trace learning rules can effectively solve the problem of learning identical weights.
Provided explanations for prior research outcomes concerning spatial invariance.
Identified specific trace learning rules as optimal for achieving invariance.

Conclusions:

Trace learning rules offer a viable mechanism for achieving spatial invariance in object recognition models.
The findings clarify a critical aspect of neural computation in the brain's ventral pathway.
Recommendations are provided for enhancing the performance of machine learning models through optimal learning rules.