In-situ ai: Towards autonomous and incremental deep learning for iot systems

M Song, K Zhong, J Zhang, Y Hu, D Liu… - … Symposium on High …, 2018 - ieeexplore.ieee.org
Recent years have seen an exploration of data volumes from a myriad of IoT devices, such
as various sensors and ubiquitous cameras. The deluge of IoT data creates enormous …

Towards unified data and lifecycle management for deep learning

H Miao, A Li, LS Davis… - 2017 IEEE 33rd …, 2017 - ieeexplore.ieee.org
Deep learning has improved state-of-the-art results in many important fields, and has been
the subject of much research in recent years, leading to the development of several systems …

Serving deep learning models with deduplication from relational databases

L Zhou, J Chen, A Das, H Min, L Yu, M Zhao… - arxiv preprint arxiv …, 2022 - arxiv.org
There are significant benefits to serve deep learning models from relational databases. First,
features extracted from databases do not need to be transferred to any decoupled deep …

Similarity caching: Theory and algorithms

G Neglia, M Garetto, E Leonardi - IEEE/ACM Transactions on …, 2021 - ieeexplore.ieee.org
This paper focuses on similarity caching systems, in which a user request for an object that
is not in the cache can be (partially) satisfied by a similar stored object, at the cost of a loss of …

Grades: Gradient descent for similarity caching

A Sabnis, TS Salem, G Neglia, M Garetto… - IEEE/ACM …, 2022 - ieeexplore.ieee.org
A similarity cache can reply to a query for an object with similar objects stored locally. In
some applications of similarity caches, queries and objects are naturally represented as …

Similarity caching: Theory and algorithms

M Garetto, E Leonardi, G Neglia - IEEE INFOCOM 2020-IEEE …, 2020 - ieeexplore.ieee.org
This paper focuses on similarity caching systems, in which a user request for an object o that
is not in the cache can be (partially) satisfied by a similar stored object o', at the cost of a loss …

Modelhub: Towards unified data and lifecycle management for deep learning

H Miao, A Li, LS Davis, A Deshpande - arxiv preprint arxiv:1611.06224, 2016 - arxiv.org
Deep learning has improved state-of-the-art results in many important fields, and has been
the subject of much research in recent years, leading to the development of several systems …

An approach for leukocytes nuclei segmentation based on image fusion

J Rawat, A Singh, HS Bhadauria - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Now day's blood smear evaluation is a most common clinical test for the hematologists. In
Most of the cases like Neutrophilia, Acute leukemia, the hematologists are eager to know …

DESIGN AND ANALYSIS OF CONTENT CACHING SYSTEMS

A Sabnis - 2023 - scholarworks.umass.edu
Caching is a simple yet powerful technique that has had a significant impact on improving
the performance of various computer systems. From internet content delivery to CPUs …

[ОПИСАНИЕ][C] ModelHUB: lifecycle management for deep learning

H Miao, A Li, LS Davis, A Deshpande - Univ. of Maryland, 2015