Search Results for author:
Found 3 papers, 0 papers with code
Lattice Quantization
In particular, we achieve ImageNet classification results close to full precision on the popular Resnet-18/50, with only 0. 5% and 5% accuracy drop for the 4-bit weights and 3-bit weights model architectures respectively.
SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikes
In this work, we analyze how the gradient can be discretized into spike events when training a spiking neural network.
A Spiking Network for Inference of Relations Trained with Neuromorphic Backpropagation
Our architecture is the first spiking neural network architecture with on-chip learning capabilities, which is able to perform relational inference on complex visual stimuli.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
