A
Amirhossein Esmaili
Researcher at University of Southern California
Publications - 18
Citations - 233
Amirhossein Esmaili is an academic researcher from University of Southern California. The author has contributed to research in topics: Scheduling (computing) & Energy consumption. The author has an hindex of 5, co-authored 16 publications receiving 120 citations.
Papers
More filters
Proceedings ArticleDOI
BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services
TL;DR: BottleNet as mentioned in this paper proposes a training method for compensating for the potential accuracy loss due to the lossy compression of features before transmitting them to the cloud, which achieves on average 5.1× improvement in end-to-end latency and 6.9× energy consumption compared with the cloud-only approach with no accuracy loss.
Proceedings ArticleDOI
Towards Collaborative Intelligence Friendly Architectures for Deep Learning
TL;DR: A new collaborative intelligence friendly architecture is designed by introducing a unit responsible for reducing the size of the feature data needed to be offloaded to the cloud to a greater extent, where this unit is placed after a selected layer of a deep model.
Proceedings ArticleDOI
SynergicLearning: neural network-based feature extraction for highly-accurate hyperdimensional learning
TL;DR: This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip and introduces a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware.
Proceedings ArticleDOI
Modeling processor idle times in MPSoC platforms to enable integrated DPM, DVFS, and task scheduling subject to a hard deadline
TL;DR: This paper presents a novel approach for modeling idle intervals in MPSoC platforms which leads to a mixed integer linear programming (MILP) formulation integrating DPM, DVFS, and task scheduling of periodic task graphs subject to a hard deadline.
Journal ArticleDOI
Energy-aware Scheduling of Task Graphs with Imprecise Computations and End-to-end Deadlines
TL;DR: This work presents a heuristic for scheduling tasks with potentially imprecise computations, represented with directed acyclic graphs, on multiprocessor platforms, and presents a mixed integer linear program formulation of the same problem, which provides the optimal reference scheduling solutions.