Information geometry of Boltzmann machines

  title={Information geometry of Boltzmann machines},
  author={Shun-ichi Amari and Koji Kurata and Hiroshi Nagaoka},
  journal={IEEE transactions on neural networks},
  volume={3 2},
A Boltzmann machine is a network of stochastic neurons. The set of all the Boltzmann machines with a fixed topology forms a geometric manifold of high dimension, where modifiable synaptic weights of connections play the role of a coordinate system to specify networks. A learning trajectory, for example, is a curve in this manifold. It is important to study the geometry of the neural manifold, rather than the behavior of a single network, in order to know the capabilities and limitations of… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 89 extracted citations

Boltzmann Machines and the EM algorithmPi erre

van de Laar, Bert, KappenLaboratory
View 9 Excerpts
Highly Influenced

A Confident Information First Principle for Parameter Reduction and Model Selection of Boltzmann Machines

IEEE Transactions on Neural Networks and Learning Systems • 2018
View 6 Excerpts
Highly Influenced

Applications of neural networks to digital communications - a survey

Signal Processing • 2000
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…