Search Results for author:
Found 3 papers, 2 papers with code
Gradient-Free Training of Recurrent Neural Networks using Random Perturbations
To this end, we extend the recently introduced activity-based node perturbation (ANP) method to operate in the time domain, leading to more efficient learning and generalization.
Broad-UNet: Multi-scale feature learning for nowcasting tasks
We introduce Broad-UNet, a novel architecture based on the core UNet model, to efficiently address this problem.
Deep brain state classification of MEG data
The experimental results of cross subject multi-class classification on the studied MEG dataset show that the inclusion of attention improves the generalization of the models across subjects.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
