Deep learning has seen a movement away from representing examples with a...
Action and observation delays commonly occur in many Reinforcement Learn...
Neuromorphic event cameras are useful for dynamic vision problems under
...
Generalizing outside of the training distribution is an open challenge f...
Reinforcement learning agents that operate in diverse and complex
enviro...
Machine learning promises methods that generalize well from finite label...
Unsupervised exploration and representation learning become increasingly...
Learning long-term dependencies in extended temporal sequences requires
...
The biological plausibility of the backpropagation algorithm has long be...
We introduce an incremental processing scheme for convolutional neural
n...
Deep networks have achieved impressive results across a variety of impor...
A major drawback of backpropagation through time (BPTT) is the difficult...
Event cameras, such as dynamic vision sensors (DVS), and dynamic and
act...
Despite their advantages in terms of computational resources, latency, a...
There is an urgent need for compact, fast, and power-efficient hardware
...
Solving constraint satisfaction problems (CSPs) is a notoriously expensi...