Electronic Colloquium on Computational Complexity, Report No. 71 (2001) Neural Circuits for Pattern Recognition with Small Total Wire Length

2001

Citations in the corpus

• Deep learning in neural networks: An overview (2014, background): “One may penalize the task-specific total length of connections (Legenstein and Maass, 2002) and communication costs of SLIM NNs implemented on the 3-dimensional brain-like multi-processor hardware to expected in the future.”
• Modular Networks: Learning to Decompose Neural Computation (2018, background): “contrast, usually only few regions of the brain are highly active simultaneously [20]. Furthermore, the modular structure of biological neural connections [28] is hypothesized to optimize energy cost [8, 15], improve adaption to changing environments and mitigate catastrophic forgetting [26]. Inspir”