Decreasing-Rate Pruning Optimizes the Construction of Efficient and Robust Distributed Networks.
Robust, efficient, and low-cost networks are advantageous in both biological and engineered systems. During neural network development in the brain, synapses are massively over-produced and then pruned-back over time. This strategy is not commonly used when designing engineered networks, since addin...
Main Authors: | Saket Navlakha, Alison L Barth, Ziv Bar-Joseph |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2015-07-01
|
Series: | PLoS Computational Biology |
Online Access: | http://europepmc.org/articles/PMC4517947?pdf=render |
Similar Items
-
A network-based approach for predicting missing pathway interactions.
by: Saket Navlakha, et al.
Published: (2012-01-01) -
Network archaeology: uncovering ancient networks from present-day interactions.
by: Saket Navlakha, et al.
Published: (2011-04-01) -
Quantization Robust Pruning With Knowledge Distillation
by: Jangho Kim
Published: (2023-01-01) -
Branch-Pipe: Improving Graph Skeletonization around Branch Points in 3D Point Clouds
by: Illia Ziamtsov, et al.
Published: (2021-09-01) -
A neural theory for counting memories
by: Sanjoy Dasgupta, et al.
Published: (2022-10-01)