A state-of-the-art convolutional neural network architecture for object detection was used to detect operating hands in open surgery videos.
Intense recent discussions have focused on how to provide individuals with control over when their data can and cannot be used --- the EU's Right To Be Forgotten regulation is an example of this effort.
The controller is trained with policy gradient to select a subgraph that maximizes the expected reward on the validation set.
We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions.
We propose Efficient Neural Architecture Search (ENAS), a faster and less expensive approach to automated model design than previous methods.
The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step.
We also show that our method performs better than competing algorithms by Welinder and Perona (2010), and by Mnih and Hinton (2012).