| Autor: |
Cassidy, Andrew S., Merolla, Paul, Arthur, John V., Esser, Steve K., Jackson, Bryan, Alvarez-Icaza, Rodrigo, Datta, Pallab, Sawada, Jun, Wong, Theodore M., Feldman, Vitaly, Amir, Arnon, Rubin, Daniel Ben-Dayan, Akopyan, Filipp, McQuinn, Emmett, Risk, William P., Modha, Dharmendra S. |
| Zdroj: |
2013 International Joint Conference on Neural Networks (IJCNN); 2013, p1-10, 10p |
| Abstrakt: |
Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards the TrueNorth cognitive computing system inspired by the brain's function and efficiency. Judiciously balancing the dual objectives of functional capability and implementation/operational cost, we develop a simple, digital, reconfigurable, versatile spiking neuron model that supports one-to-one equivalence between hardware and simulation and is implementable using only 1272 ASIC gates. Starting with the classic leaky integrate-and-fire neuron, we add: (a) configurable and reproducible stochasticity to the input, the state, and the output; (b) four leak modes that bias the internal state dynamics; (c) deterministic and stochastic thresholds; and (d) six reset modes for rich finite-state behavior. The model supports a wide variety of computational functions and neural codes. We capture 50+ neuron behaviors in a library for hierarchical composition of complex computations and behaviors. Although designed with cognitive algorithms and applications in mind, serendipitously, the neuron model can qualitatively replicate the 20 biologically-relevant behaviors of a dynamical neuron model. [ABSTRACT FROM PUBLISHER] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
