354 citations
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- Indian Institute of Science BangaloreIN6 papers
- Indian Institute of Technology DelhiIN6 papers
- Microsoft (United States)US6 papers
- Indian Institute of Technology KharagpurIN5 papers
- Birla Institute of Technology and Science, Pilani - Goa CampusIN4 papers
- Indian Institute of Technology KanpurIN4 papers
- Carnegie Mellon UniversityUS3 papers
- Geometric (India)IN3 papers
- Laboratoire d'Informatique de l'École PolytechniqueFR3 papers
- Microsoft Research (United Kingdom)GB3 papers
- Stanford UniversityUS3 papers
5 papers · 1 filter
Assessment of the Relative Importance of different hyper-parameters of LSTM for an IDS
Mohit Sewak, Sanjay K. Sahay, Hemant Rathore
Recurrent deep learning language models like the LSTM are often used to provide advanced cyber-defense for high-value assets. The underlying assumption for using LSTM networks for…
Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads
Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka +2
Specialized accelerators such as GPUs, TPUs, FPGAs, and custom ASICs have been increasingly deployed to train deep learning models. These accelerators exhibit heterogeneous perform…
WattScale: A Data-driven Approach for Energy Efficiency Analytics of Buildings at Scale
Srinivasan Iyengar, Stephen Lee, David Irwin +2
Buildings consume over 40% of the total energy in modern societies, and improving their energy efficiency can significantly reduce our energy footprint. In this paper, we present \…
Emission-aware Energy Storage Scheduling for a Greener Grid
Rishikesh Jha, Stephen Lee, Srinivasan Iyengar +3
Reducing our reliance on carbon-intensive energy sources is vital for reducing the carbon footprint of the electric grid. Although the grid is seeing increasing deployments of clea…
Extreme Regression for Dynamic Search Advertising
Yashoteja Prabhu, Aditya Kusupati, Nilesh Gupta +1
This paper introduces a new learning paradigm called eXtreme Regression (XR) whose objective is to accurately predict the numerical degrees of relevance of an extremely large numbe…