Deep Learning
Learning long-range spatial dependencies with horizontal gated recurrent units
Drew Linsley, Junkyung Kim, Vijay Veerabadran, Charles Windolf, Thomas Serre
We introduce a visual challenge, Pathfinder, and describe a novel recurrent neural network architecture called the horizontal gated recurrent unit (hGRU) to learn intrinsic horizontal connections - both within and across feature columns.
Compositional generalization through meta sequence-to-sequence learning
Neural Information Processing Systems http://nips.cc/
Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity
Aria Wang, Michael Tarr, Leila Wehbe
Neural Information Processing Systems http://nips.cc/
Step Size Matters in Deep Learning
Neural Information Processing Systems http://nips.cc/
