Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines
In the past three decades, many theoretical measures of complexity have been proposed to help understand complex systems. In this work, for the first time, we place these measures on a level playing field, to explore the qualitative similarities and differences between them, and their shortcomings....
Main Authors: | Maxinder S. Kanwal, Joshua A. Grochow, Nihat Ay |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-07-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/19/7/310 |
Similar Items
-
Boltzmann Machines as Generalized Hopfield Networks: A Review of Recent Results and Outlooks
by: Chiara Marullo, et al.
Published: (2020-12-01) -
Information Geometry Formalism for the Spatially Homogeneous Boltzmann Equation
by: Bertrand Lods, et al.
Published: (2015-06-01) -
Extending the Extreme Physical Information to Universal Cognitive Models via a Confident Information First Principle
by: Xiaozhao Zhao, et al.
Published: (2014-07-01) -
Boltzmann Complexity: An Emergent Property of the Majorization Partial Order
by: William Seitz, et al.
Published: (2016-09-01) -
Information Geometry on Complexity and Stochastic Interaction
by: Nihat Ay
Published: (2015-04-01)