75 citations · 428 across the 18 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 22 cited
Adaptive Learning Rate Clipping Stabilizes Learning
Jeffrey M. Ede, Richard Beanland
Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch s…
eess.IV2019★ 46 cited
Partial Scanning Transmission Electron Microscopy with Deep Learning
Jeffrey M. Ede, Richard Beanland
Compressed sensing algorithms are used to decrease electron microscope scan time and electron beam exposure with minimal information loss. Following successful applications of deep…