Country
Random Projections and Sampling Algorithms for Clustering of High-Dimensional Polygonal Curves
Stefan Meintrup, Alexander Munteanu, Dennis Rohde
Neural Information Processing Systems http://nips.cc/
ae07d152c51ea2ddae65aa7192eb5ff7-Supplemental-Conference.pdf
Recent work has shown that a much simpler model, simple graph convolution (SGC) (Wu et al., 2019),iscompetitivewithGCNs incommon graph machine learning benchmarks.
Hyperspherical Prototype Networks
Pascal Mettes, Elise van der Pol, Cees Snoek
Neural Information Processing Systems http://nips.cc/
LimitstoDepth-EfficienciesofSelf-Attention
Self-attention architectures, which are rapidly pushing the frontier innatural language processing, demonstrate asurprising depth-inefficient behavior: previous works indicate that increasing the internal representation (network width) isjust as useful as increasing the number of self-attention layers (network depth).
d03a857a23b5285736c4d55e0bb067c8-Paper.pdf
Examples include M/EEG inverse problems, neural encoding models for task-based fMRI analyses, and climate science.