Neural Information Processing Systems http://nips.cc/

V oice Assistants (V As) such as Amazon Alexa or Google Assistant rely on wake-word detection to respond to people's commands, which could potentially be vulnerable to audio adversarial examples. In this work, we target our attack on the wake-word detection system, jamming the model with some inconspicuous background music to deactivate the V As while our audio adversary is present. We implemented an emulated wake-word detection system of Amazon Alexa based on recent publications.

This basic formula has seen almost universal adoption across many different medical specialties.

To address this shortcoming, we introduce'Graph Structured Prediction Energy Networks,' for which we develop inference techniques that allow to both model explicit local and implicit

Neural Information Processing Systems http://nips.cc/

This can uncover some of the "attended"

Unlike the seminal work of taskonomy that relies on a large number of annotations as supervision and is thus computationally cumbersome, the proposed approach requires no human annotations and imposes no constraints on the architectures of the networks.

After learning the novel classes, the model is then evaluated on the overall classification performance on both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Network, which regularizes the learning of novel classes. In each episode, we train a set of new weights to recognize novel classes until they converge, and we show that the technique of recurrent back-propagation can back-propagate through the optimization process and facilitate the learning of these parameters.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/