401 citations · 402 across the 3 of their papers we have counts for
3 papers
SPADE: Self-supervised Pretraining for Acoustic DisEntanglement
John Harvill, Jarred Barber, Arun Nair +1
Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in d…
Appliance Level Short-term Load Forecasting via Recurrent Neural Network
Yuqi Zhou, Arun Sukumaran Nair, David Ganger +3
Accurate load forecasting is critical for electricity market operations and other real-time decision-making tasks in power systems. This paper considers the short-term load forecas…
Massively Parallel Methods for Deep Reinforcement Learning
Arun Nair, Praveen Srinivasan, Sam Blackwell +11
We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; p…