Zobrazeno 1 - 10
of 92
pro vyhledávání: '"Willke, Theodore L."'
Autor:
Duan, Shukai, Ping, Heng, Kanakaris, Nikos, Xiao, Xiongye, Zhang, Peiyu, Kyriakis, Panagiotis, Ahmed, Nesreen K., Ma, Guixiang, Capota, Mihai, Nazarian, Shahin, Willke, Theodore L., Bogdan, Paul
Existing approaches for device placement ignore the topological features of computation graphs and rely mostly on heuristic methods for graph partitioning. At the same time, they either follow a grouper-placer or an encoder-placer architecture, which
Externí odkaz:
http://arxiv.org/abs/2405.14185
Autor:
Chen, Le, Ahmed, Nesreen K., Dutta, Akash, Bhattacharjee, Arijit, Yu, Sixing, Mahmud, Quazi Ishtiaque, Abebe, Waqwoya, Phan, Hung, Sarkar, Aishwarya, Butler, Branden, Hasabnis, Niranjan, Oren, Gal, Vo, Vy A., Munoz, Juan Pablo, Willke, Theodore L., Mattson, Tim, Jannesari, Ali
Recently, language models (LMs), especially large language models (LLMs), have revolutionized the field of deep learning. Both encoder-decoder models and prompt-based techniques have shown immense potential for natural language processing and code-ba
Externí odkaz:
http://arxiv.org/abs/2402.02018
Autor:
Duan, Shukai, Kanakaris, Nikos, Xiao, Xiongye, Ping, Heng, Zhou, Chenyu, Ahmed, Nesreen K., Ma, Guixiang, Capota, Mihai, Willke, Theodore L., Nazarian, Shahin, Bogdan, Paul
Code optimization is a daunting task that requires a significant level of expertise from experienced programmers. This level of expertise is not sufficient when compared to the rapid development of new hardware architectures. Towards advancing the wh
Externí odkaz:
http://arxiv.org/abs/2312.05657
Autor:
Ma, Guixiang, Xiao, Yao, Willke, Theodore L., Ahmed, Nesreen K., Nazarian, Shahin, Bogdan, Paul
High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems.The rapid increas
Externí odkaz:
http://arxiv.org/abs/2010.04414
The terms multi-task learning and multitasking are easily confused. Multi-task learning refers to a paradigm in machine learning in which a network is trained on various related tasks to facilitate the acquisition of tasks. In contrast, multitasking
Externí odkaz:
http://arxiv.org/abs/2007.10527
In many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search. Recently, the
Externí odkaz:
http://arxiv.org/abs/1912.11615
Autor:
Turek, Javier S., Jain, Shailee, Vo, Vy, Capota, Mihai, Huth, Alexander G., Willke, Theodore L.
Recent work has shown that topological enhancements to recurrent neural networks (RNNs) can increase their expressiveness and representational capacity. Two popular enhancements are stacked RNNs, which increases the capacity for learning non-linear f
Externí odkaz:
http://arxiv.org/abs/1909.00021
Autor:
Anderson, Michael J., Tamir, Jonathan I., Turek, Javier S., Alley, Marcus T., Willke, Theodore L., Vasanawala, Shreyas S., Lustig, Michael
Magnetic resonance imaging is capable of producing volumetric images without ionizing radiation. Nonetheless, long acquisitions lead to prohibitively long exams. Compressed sensing (CS) can enable faster scanning via sub-sampling with reduced artifac
Externí odkaz:
http://arxiv.org/abs/1809.04195
Autor:
Vyas, Apoorv, Jammalamadaka, Nataraj, Zhu, Xia, Das, Dipankar, Kaul, Bharat, Willke, Theodore L.
As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this wor
Externí odkaz:
http://arxiv.org/abs/1809.03576
For a deep learning model, efficient execution of its computation graph is key to achieving high performance. Previous work has focused on improving the performance for individual nodes of the computation graph, while ignoring the parallelization of
Externí odkaz:
http://arxiv.org/abs/1807.09667