The Devil and the Network: What Sparsity Implies to Robustness and Memory
Abstract
Robustness is a commonly bruited property of neural networks; in particu(cid:173) lar, a folk theorem in neural computation asserts that neural networks-in contexts with large interconnectivity-continue to function efficiently, al(cid:173) beit with some degradation, in the presence of component damage or loss. A second folk theorem in such contexts asserts that dense interconnectiv(cid:173) ity between neural elements is a sine qua non for the efficient usage of resources. These premises are formally examined in this communication in a setting that invokes the notion of the "devil" 1 in the network as an agent that produces sparsity by snipping connections.
Cite
Text
Biswas and Venkatesh. "The Devil and the Network: What Sparsity Implies to Robustness and Memory." Neural Information Processing Systems, 1990.Markdown
[Biswas and Venkatesh. "The Devil and the Network: What Sparsity Implies to Robustness and Memory." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/biswas1990neurips-devil/)BibTeX
@inproceedings{biswas1990neurips-devil,
title = {{The Devil and the Network: What Sparsity Implies to Robustness and Memory}},
author = {Biswas, Sanjay and Venkatesh, Santosh S.},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {883-889},
url = {https://mlanthology.org/neurips/1990/biswas1990neurips-devil/}
}