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

Search research articles

Related Experiment Videos

Beyond the binary Boltzmann machine.

N H Anderson¹, D M Titterington

¹Dept. of Stat., Glasgow Univ.

IEEE Transactions on Neural Networks

|January 1, 1995

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Use of <sup>13</sup>C/<sup>12</sup>C to trace dissolved and particulate organic matter utilization by populations of an aquatic invertebrate.

Oecologia·2017

Same author

Integration psychophysics is not traditional psychophysics.

The Behavioral and brain sciences·2014

Same author

Some psycholinguistic aspects of person perception.

Memory & cognition·2013

Same author

Maternal and pathological pregnancy characteristics in customised birthweight centiles and identification of at-risk small-for-gestational-age infants: a retrospective cohort study.

BJOG : an international journal of obstetrics and gynaecology·2012

Same author

The impact of maternal body mass index on the phenotype of pre-eclampsia: a prospective cohort study.

BJOG : an international journal of obstetrics and gynaecology·2012

Same author

Integration of intention and outcome in moral judgment.

Memory & cognition·2011

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces polytomous Boltzmann machines, extending binary models to handle multicategory responses. The new model uses statistical methods for training, offering a more flexible approach to machine learning.

Area of Science:

Machine Learning
Statistical Modeling
Artificial Intelligence

Background:

Traditional Boltzmann machines are limited to binary (0 or 1) neuron outputs.
There is a need for models that can handle more complex, categorical data.

Purpose of the Study:

To extend the standard Boltzmann machine to accommodate polytomous (multicategory) neuron responses.
To define updating rules and stationary distributions for the generalized model.
To present a training method using alternating minimization.

Main Methods:

Generalization of the Boltzmann machine architecture for polytomous variables.
Definition of stochastic updating rules and derivation of stationary distributions.
Application of alternating minimization, drawing parallels with polytomous logistic regression, iterative proportional fitting, and the EM algorithm.

Related Experiment Videos

Main Results:

Successfully extended the Boltzmann machine framework to handle multicategory data.
Established the theoretical underpinnings, including updating rules and stationary distributions.
Demonstrated the efficacy of the alternating minimization training procedure.

Conclusions:

The proposed polytomous Boltzmann machine offers a more versatile alternative to binary models for categorical data.
The integration of statistical concepts enhances the model's theoretical foundation and practical applicability.
This generalization opens new avenues for applying Boltzmann machines in diverse fields requiring multicategory data analysis.