Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons
Abstract
A non–linear dynamic system is called contracting if initial conditions are for- gotten exponentially fast, so that all trajectories converge to a single trajectory. We use contraction theory to derive an upper bound for the strength of recurrent connections that guarantees contraction for complex neural networks. Specifi- cally, we apply this theory to a special class of recurrent networks, often called Cooperative Competitive Networks (CCNs), which are an abstract representation of the cooperative-competitive connectivity observed in cortex. This specific type of network is believed to play a major role in shaping cortical responses and se- lecting the relevant signal among distractors and noise. In this paper, we analyze contraction of combined CCNs of linear threshold units and verify the results of our analysis in a hybrid analog/digital VLSI CCN comprising spiking neurons and dynamic synapses.
Cite
Text
Neftci et al. "Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons." Neural Information Processing Systems, 2007.Markdown
[Neftci et al. "Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/neftci2007neurips-contraction/)BibTeX
@inproceedings{neftci2007neurips-contraction,
title = {{Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons}},
author = {Neftci, Emre and Chicca, Elisabetta and Indiveri, Giacomo and Slotine, Jean-jeacques and Douglas, Rodney J.},
booktitle = {Neural Information Processing Systems},
year = {2007},
pages = {1073-1080},
url = {https://mlanthology.org/neurips/2007/neftci2007neurips-contraction/}
}