HIGHLIGHTS
- who: Erwann Martin from the Research and Technology, Palaiseau, France have published the research work: EqSpike: Spike-driven equilibrium propagation for neuromorphic implementations, in the Journal: (JOURNAL) of March/19,/2021
- what: The authors show that implemented in silicon neuromorphic technology could reduce the energy consumption of inference and training respectively by three orders and two orders of magnitude compared to graphics processing units. The authors propose a different approach to training spiking neural_networks with high accuracy while using a local, two-factor learning rule compatible with neuromorphic implementations and scalable to complex tasks. The . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.