Tiny-CRNN: Streaming Wakeword Detection In A Low Footprint Setting

Autor: Khursheed, Mohammad Omar, Jose, Christin, Kumar, Rajath, Fu, Gengshen, Kulis, Brian, Cheekatmalla, Santosh Kumar

In this work, we propose Tiny-CRNN (Tiny Convolutional Recurrent Neural Network) models applied to the problem of wakeword detection, and augment them with scaled dot product attention. We find that, compared to Convolutional Neural Network models, F

Externí odkaz: http://arxiv.org/abs/2109.14725

Multi-task Learning for Continuous Control

Autor: Arora, Himani, Kumar, Rajath, Krone, Jason, Li, Chong

Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the

Externí odkaz: http://arxiv.org/abs/1802.01034

Prediction of Queue Waiting Times for Metascheduling on Parallel Batch Systems.

Autor: Kumar, Rajath, Vadhiyar, Sathish

Publikováno v: Job Scheduling Strategies for Parallel Processing 18th International Workshop, JSSPP 2014, Phoenix, AZ, USA, May 23, 2014. Revised Selected Papers; 2015, p108-128, 21p