Computational power of neural networks: a characterization in terms of Kolmogorov complexity
Work
Year: 1997
Type: article
Abstract: The computational power of recurrent neural networks is shown to depend ultimately on the complexity of the real constants (weights) of the network. The complexity, or information contents, of the wei... more
Cites: 31
Cited by: 93
Related to: 10
FWCI: 5.339
Citation percentile (by year/subfield): 97.46
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Sustainable Development Goal Decent work and economic growth
Open Access status: green