Search Results for author:
Found 9 papers, 1 papers with code
Federated Learning under Distributed Concept Drift
Federated Learning (FL) under distributed concept drift is a largely unexplored area.
FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations
To address these challenges, we leverage Federated Learning (FL), where ground stations and satellites collaboratively train a global ML model without sharing the captured images on the satellites.
Interpret-able feedback for AutoML systems
Automated machine learning (AutoML) systems aim to enable training machine learning (ML) models for non-ML experts.
Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
Compressed models that are deployed on the edge servers for inference suffer from data drift, where the live video data diverges from the training data.
Machine Learning Systems for Highly-Distributed and Rapidly-Growing Data
The usability and practicality of any machine learning (ML) applications are largely influenced by two critical but hard-to-attain factors: low latency and low cost.
The Non-IID Data Quagmire of Decentralized Machine Learning
Our study shows that: (i) skewed data labels are a fundamental and pervasive problem for decentralized learning, causing significant accuracy loss across many ML applications, DNN models, training datasets, and decentralized learning algorithms; (ii) the problem is particularly challenging for DNN models with batch normalization; and (iii) the degree of data skew is a key determinant of the difficulty of the problem.
Enabling the Adoption of Processing-in-Memory: Challenges, Mechanisms, Future Research Directions
This requires efficient mechanisms that can provide logic in DRAM with access to CPU structures without having to communicate frequently with the CPU.
Hardware Architecture
Focus: Querying Large Video Datasets with Low Latency and Low Cost
Focus handles the lower accuracy of the cheap CNNs by judiciously leveraging expensive CNNs at query-time.
D-SLATS: Distributed Simultaneous Localization and Time Synchronization
Therefore, we propose D-SLATS, a framework comprised of three different and independent algorithms to jointly solve time synchronization and localization problems in a distributed fashion.
