Timezone: »

 
Spotlight
Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons
Emre Neftci · Elisabetta Chicca · Giacomo Indiveri · Jean-Jacques Slotine · Rodney J Douglas

Wed Dec 05 05:20 PM -- 05:30 PM (PST) @ None

A non--linear dynamic system is called contracting if initial conditions are forgotten exponentially fast, so that all trajectories converge to a single trajectory which is the solution of the system. We use contraction theory to derive an upper bound for the strength of recurrent connections that guarantees contraction for complex neural networks. Specifically, we apply this theory to a special class of recurrent networks which are an abstract representation of the cooperative-competitive connectivity observed in cortex and often called Cooperative Competitive Networks (CCNs). This specific type of network is believed to play a major role in shaping cortical responses and selecting 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.

Author Information

Emre Neftci (Institute of Neuroinformatics)
Elisabetta Chicca (Bielefeld University)
Giacomo Indiveri (ETH Zurich)
Jean-Jacques Slotine (Massachusetts Institute of Technology)
Rodney J Douglas (Institute of Neuroinformatics)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors