Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Jajal, Purvish"'
Autor:
Jajal, Purvish, Eliopoulos, Nick John, Chou, Benjamin Shiue-Hal, Thiravathukal, George K., Davis, James C., Lu, Yung-Hsiang
We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understand
Externí odkaz:
http://arxiv.org/abs/2409.07613
Autor:
Eliopoulos, Nick John, Jajal, Purvish, Davis, James C., Liu, Gaowen, Thiravathukal, George K., Lu, Yung-Hsiang
This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation. However, these
Externí odkaz:
http://arxiv.org/abs/2407.05941
Autor:
Davis, James C., Jajal, Purvish, Jiang, Wenxin, Schorlemmer, Taylor R., Synovic, Nicholas, Thiruvathukal, George K.
Deep neural networks (DNNs) achieve state-of-the-art performance in many areas, including computer vision, system configuration, and question-answering. However, DNNs are expensive to develop, both in intellectual effort (e.g., devising new architect
Externí odkaz:
http://arxiv.org/abs/2404.16688
Autor:
Tung, Caleb, Eliopoulos, Nicholas, Jajal, Purvish, Ramshankar, Gowri, Yang, Chen-Yun, Synovic, Nicholas, Zhang, Xuecen, Chaudhary, Vipin, Thiruvathukal, George K., Lu, Yung-Hsiang
Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requirements. Producing more energy-efficient CNNs often requires model trainin
Externí odkaz:
http://arxiv.org/abs/2310.07782
Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem
Autor:
Jajal, Purvish, Jiang, Wenxin, Tewari, Arav, Kocinare, Erik, Woo, Joseph, Sarraf, Anusha, Lu, Yung-Hsiang, Thiruvathukal, George K., Davis, James C.
Software engineers develop, fine-tune, and deploy deep learning (DL) models using a variety of development frameworks and runtime environments. DL model converters move models between frameworks and to runtime environments. Conversion errors compromi
Externí odkaz:
http://arxiv.org/abs/2303.17708
Autor:
Jiang, Wenxin, Synovic, Nicholas, Jajal, Purvish, Schorlemmer, Taylor R., Tewari, Arav, Pareek, Bhavesh, Thiruvathukal, George K., Davis, James C.
Due to the cost of developing and training deep learning models from scratch, machine learning engineers have begun to reuse pre-trained models (PTMs) and fine-tune them for downstream tasks. PTM registries known as "model hubs" support engineers in
Externí odkaz:
http://arxiv.org/abs/2303.08934
Autor:
Lyu, Xingzheng1 (AUTHOR) frankly@zju.edu.cn, Jajal, Purvish2 (AUTHOR), Tahir, Muhammad Zeeshan1 (AUTHOR), Zhang, Sanyuan1 (AUTHOR)
Publikováno v:
Scientific Reports. 7/13/2022, Vol. 12 Issue 1, p1-13. 13p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.