Search Results for author:
Found 3 papers, 0 papers with code
Information Bottleneck-Based Hebbian Learning Rule Naturally Ties Working Memory and Synaptic Updates
The global component computes a layer-wise modulatory signal that depends on a batch of samples.
Accelerating Deep Learning with Dynamic Data Pruning
Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data.
BlurNet: Defense by Filtering the Feature Maps
First, we motivate the defense with a frequency analysis of the first layer feature maps of the network on the LISA dataset, which shows that high frequency noise is introduced into the input image by the $RP_2$ algorithm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
