Name
Title | ||
|---|---|---|
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. |
Year | Venue | Keywords |
|---|---|---|
2007 | NIPS | neural network,upper bound,initial condition,contract theory |
Field | DocType | Citations |
Contraction (grammar),Computer science,Upper and lower bounds,Artificial intelligence,Contraction (operator theory),Artificial neural network,Very-large-scale integration,Trajectory,Machine learning,Exponential growth | Conference | 5 |
PageRank | References | Authors |
0.49 | 9 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Emre Neftci | 1 | 183 | 17.52 |
| Elisabetta Chicca | 2 | 584 | 49.28 |
| Giacomo Indiveri | 3 | 1460 | 148.21 |
| Jean-jacques E. Slotine | 4 | 2878 | 344.39 |
| Rodney J. Douglas | 5 | 593 | 242.90 |