关注
Urmish Thakker
Urmish Thakker
其他姓名Urmish Ajit Thakker
Deep Learning Research, SambaNova Systems
在 wisc.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Multitask Prompted Training Enables Zero-Shot Task Generalization
V Sanh, A Webson, C Raffel, S Bach, L Sutawika, Z Alyafeai, A Chaffin, ...
International Conference on Learning Representations, 2022
13392022
Bloom: A 176b-parameter open-access multilingual language model
T Le Scao, A Fan, C Akiki, E Pavlick, S Ilić, D Hesslow, R Castagné, ...
12782023
A survey on federated learning for resource-constrained iot devices
A Imteaj, U Thakker, S Wang, J Li, MH Amini
IEEE Internet of Things Journal 9 (1), 1-24, 2021
3992021
Benchmarking TinyML Systems: Challenges and Direction
CR Banbury, VJ Reddi, M Lam, W Fu, A Fazel, J Holleman, X Huang, ...
MLSys 2020 Workshop, 2020
265*2020
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
SH Bach, V Sanh, ZX Yong, A Webson, C Raffel, NV Nayak, A Sharma, ...
ACL Demos 2022, 2022
2562022
MicroNets: Neural network architectures for deploying TinyML applications on commodity microcontrollers
C Banbury, C Zhou, I Fedorov, R Matas, U Thakker, D Gope, ...
Proceedings of Machine Learning and Systems 3, 2021
2402021
Mlperf tiny benchmark
C Banbury, VJ Reddi, P Torelli, J Holleman, N Jeffries, C Kiraly, P Montino, ...
NeurIPS 2021, 2021
1702021
Federated Learning for Resource-Constrained IoT Devices: Panoramas and State of the Art
A Imteaj, K Mamun Ahmed, U Thakker, S Wang, J Li, MH Amini
Federated and Transfer Learning 27, 7-27, 2023
542023
Compressing RNNs to kilobyte budget for IoT devices using Kronecker products
U Thakker, I Fedorov, C Zhou, D Gope, M Mattina, G Dasika, J Beu
ACM Journal on Emerging Technologies in Computing Systems (JETC) 17 (4), 1-18, 2021
49*2021
Run-Time Efficient RNN Compression for Inference on Edge Devices
U Thakker, J Beu, D Gope, G Dasika, M Matthew
4th edition of Workshop on Energy Efficient Machine Learning and Cognitive …, 2019
292019
Skipping rnn state updates without retraining the original model
J Tao, U Thakker, G Dasika, J Beu
Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor …, 2019
192019
Ternary MobileNets via Per-Layer Hybrid Filter Banks
D Gope, J Beu, U Thakker, M Mattina
CVPR Workshop 2020, 2019
182019
Measuring scheduling efficiency of RNNs for NLP applications
U Thakker, J Beu, G Dasika, M Mattina
6th edition of International Workshop on Performance Analysis of Machine …, 2019
172019
Pushing the limits of RNN Compression
U Thakker, I Fedorov, J Beu, D Gope, C Zhou, G Dasika, M Mattina
5th edition of Workshop on Energy Efficient Machine Learning and Cognitive …, 2019
162019
A Static Analysis-based Cross-Architecture Performance Prediction Using Machine Learning
N Ardalani, U Thakker, A Albarghouthi, K Sankaralingam
2nd International Workshop on AI-assisted Design for Architecture co-located …, 2019
152019
Compressing Language Models using Doped Kronecker Products
U Thakker, P Whatmough, M Mattina, J Beu
On Device Intelligence Workshop at Third Conference on Machine Learning and …, 2020
142020
Doping: A technique for extreme compression of lstm models using sparse structured additive matrices
U Thakker, P Whatmough, Z Liu, M Mattina, J Beu
Proceedings of machine learning and systems 3, 533-549, 2021
11*2021
Rank and run-time aware compression of NLP Applications
U Thakker, J Beu, D Gope, G Dasika, M Mattina
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language …, 2020
112020
Understanding the impact of dynamic channel pruning on conditionally parameterized convolutions
R Raju, D Gope, U Thakker, J Beu
Proceedings of the 2nd International Workshop on Challenges in Artificial …, 2020
72020
Aggressive Compression of MobileNets Using Hybrid Ternary Layers
D Gope, J Beu, U Thakker, M Mattina
2nd edition of the tinyML Summit, 2020
62020
系统目前无法执行此操作,请稍后再试。
文章 1–20