• DOI:10.3390/e19070310
Corpus ID: 5418300

Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines

@article{Kanwal2017ComparingIM,
  title={Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines},
  author={Maxinder S. Kanwal and Joshua A. Grochow and N. Ay},
  journal={Entropy},
  year={2017},
  volume={19},
  pages={310}
}

Maxinder S. Kanwal, Joshua A. Grochow, N. Ay

Published 2017

Computer Science, Mathematics, Biology

Entropy

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. Specifically, using the Boltzmann machine architecture (a fully connected recurrent neural network) with uniformly distributed weights as our model of study, we numerically measure how complexity… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed