no code implementations • 4 May 2019 • Zach Dwiel, Madhavun Candadai, Mariano Phielipp, Arjun K. Bansal
Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transferability of sub-policies to tasks outside the training distribution.
1 code implementation • 24 Jan 2018 • Scott Cyphers, Arjun K. Bansal, Anahita Bhiwandiwalla, Jayaram Bobba, Matthew Brookhart, Avijit Chakraborty, Will Constable, Christian Convey, Leona Cook, Omar Kanawi, Robert Kimball, Jason Knight, Nikolay Korovaiko, Varun Kumar, Yixing Lao, Christopher R. Lishka, Jaikrishnan Menon, Jennifer Myers, Sandeep Aswath Narayana, Adam Procter, Tristan J. Webb
The current approach, which we call "direct optimization", requires deep changes within each framework to improve the training performance for each hardware backend (CPUs, GPUs, FPGAs, ASICs) and requires $\mathcal{O}(fp)$ effort; where $f$ is the number of frameworks and $p$ is the number of platforms.
no code implementations • NeurIPS 2017 • Urs Köster, Tristan J. Webb, Xin Wang, Marcel Nassar, Arjun K. Bansal, William H. Constable, Oğuz H. Elibol, Scott Gray, Stewart Hall, Luke Hornof, Amir Khosrowshahi, Carey Kloss, Ruby J. Pai, Naveen Rao
Here we present the Flexpoint data format, aiming at a complete replacement of 32-bit floating point format training and inference, designed to support modern deep network topologies without modifications.
no code implementations • arXiv 2015 • Brian Cheung, Jesse A. Livezey, Arjun K. Bansal, Bruno A. Olshausen
Deep learning has enjoyed a great deal of success because of its ability to learnuseful features for tasks such as classification.
1 code implementation • 20 Dec 2014 • Brian Cheung, Jesse A. Livezey, Arjun K. Bansal, Bruno A. Olshausen
Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification.