Search Results for author:
Found 2 papers, 0 papers with code
Spike-based computation using classical recurrent neural networks
We show that this new network can achieve performance comparable to other types of spiking networks in the MNIST benchmark and its variants, the Fashion-MNIST and the Neuromorphic-MNIST.
Warming up recurrent neural networks to maximise reachable multistability greatly improves learning
This insight leads to the design of a novel way to initialise any recurrent cell connectivity through a procedure called "warmup" to improve its capability to learn arbitrarily long time dependencies.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
