Urmish Thakker

2.1k total citations · 1 hit paper
8 papers, 511 citations indexed

About

Urmish Thakker is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing. According to data from OpenAlex, Urmish Thakker has authored 8 papers receiving a total of 511 indexed citations (citations by other indexed papers that have themselves been cited), including 7 papers in Artificial Intelligence, 4 papers in Computer Vision and Pattern Recognition and 2 papers in Signal Processing. Recurrent topics in Urmish Thakker's work include Advanced Neural Network Applications (3 papers), Neural Networks and Applications (2 papers) and Topic Modeling (2 papers). Urmish Thakker is often cited by papers focused on Advanced Neural Network Applications (3 papers), Neural Networks and Applications (2 papers) and Topic Modeling (2 papers). Urmish Thakker collaborates with scholars based in United States. Urmish Thakker's co-authors include Shiqiang Wang, Ahmed Imteaj, M. Hadi Amini, Jian Li, Ganesh Dasika, Matthew Mattina, Igor Fedorov, Colby Banbury, Xueqin Huang and Vijay Janapa Reddi and has published in prestigious journals such as IEEE Internet of Things Journal and ACM Journal on Emerging Technologies in Computing Systems.

In The Last Decade

Urmish Thakker

8 papers receiving 496 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

A Survey on Federated Learning for Resource-Constrained IoT Devices

2021 473 citations Ahmed Imteaj, Urmish Thakker et al. IEEE Internet of Things Journal profile →

Peers

Urmish Thakker

AI

CNC

EEE

IS

CSA

Jed Mills United Kingdom

Dian Shi China

Bong Jun Ko United States

Zeyi Tao United States

Zhiyuan Wang China

Hongbin Zhu China

Wenjing Zhang China

Liantao Wu China

Víctor Valls Ireland

Travis Mayberry United States

Jed Mills United Kingdom

Urmish Thakker

489 ×1.2

AI

224 ×1.2

CNC

157 ×1.6

EEE

123 ×1.6

IS

97 ×1.8

CSA

Citations per year, relative to Urmish Thakker Urmish Thakker (= 1×) peers Jed Mills

Countries citing papers authored by Urmish Thakker

Since Specialization

Citations

This map shows the geographic impact of Urmish Thakker's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Urmish Thakker with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Urmish Thakker more than expected).

Fields of papers citing papers by Urmish Thakker

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Urmish Thakker. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Urmish Thakker. The network helps show where Urmish Thakker may publish in the future.

Co-authorship network of co-authors of Urmish Thakker

This figure shows the co-authorship network connecting the top 25 collaborators of Urmish Thakker. A scholar is included among the top collaborators of Urmish Thakker based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Urmish Thakker. Urmish Thakker is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

8 of 8 papers shown

1.

Li, Bo, et al.. (2024). SambaLingo: Teaching Large Language Models New Languages. 1–21. 3 indexed citations

2.

Thakker, Urmish, et al.. (2021). Doping: A technique for Extreme Compression of LSTM Models using Sparse Structured Additive Matrices. 3. 533–549. 2 indexed citations

3.

Imteaj, Ahmed, Urmish Thakker, Shiqiang Wang, Jian Li, & M. Hadi Amini. (2021). A Survey on Federated Learning for Resource-Constrained IoT Devices. IEEE Internet of Things Journal. 9(1). 1–24. 473 indexed citations breakdown →

4.

Thakker, Urmish, et al.. (2021). Compressing RNNs to Kilobyte Budget for IoT Devices Using Kronecker Products. ACM Journal on Emerging Technologies in Computing Systems. 17(4). 1–18. 5 indexed citations

5.

Banbury, Colby, Chuteng Zhou, Igor Fedorov, et al.. (2020). MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers. 3. 517–532. 6 indexed citations

6.

Thakker, Urmish, et al.. (2020). Understanding the Impact of Dynamic Channel Pruning on Conditionally Parameterized Convolutions. 27–33. 5 indexed citations

7.

Huang, Xueqin, et al.. (2020). Pushing the Envelope of Dynamic Spatial Gating technologies. 21–26. 4 indexed citations

8.

Thakker, Urmish, et al.. (2019). Skipping RNN State Updates without Retraining the Original Model. 31–36. 13 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact