TH4.R12.4
A DOCKER-BASED FRAMEWORK FOR PARALLEL HYPERPARAMETER TUNING OF LSTM MODELS
Anusha Srirenganathan Malarvizhi, George Mason University, United States; Tayven Stover, Northern Virginia Community College, United States; Seren Smith, George Mason University, United States; Kaylee Smith, University of Michigan, United States; Zifu Wang, Harvard University, United States; Chaowei Yang, George Mason University, United States
Session:
TH4.R12: High-Performance and Efficient Learning Frameworks for Remote Sensing Oral
Track:
AI and Big Data
Location:
TBD
Presentation Time:
Thu, 13 Aug, 17:00 - 17:15
Session Chair:
Gabriele Cavallaro, University of Iceland
Presentation
Discussion
Resources
No resources available.
Session TH4.R12
TH4.R12.1: SC-DBNET: AN EFFICIENT SPECTRAL-CONDITIONED DUAL-BRANCH NET FOR HSI CLASSIFICATION
Jihun Kim, Jungkwon Kim, Chi Zhang, JEONGHYEON PARK, Kwangsun Yoo, Seok-Joo Byun, ELROILAB, Korea (South)
TH4.R12.2: ENERGY EFFICIENT GPU FREQUENCY SCALING FOR GEOSPATIAL FOUNDATION MODELS
Joseph Arnold Xavier, Rocco Sedona, Forschungszentrum Jülich, Germany; Morris Riedel, Gabriele Cavallaro, University of Iceland, Iceland
TH4.R12.3: FROGNER: ANCHOR-DRIVEN NEURAL GAUSSIAN REPRESENTATION FOR COMPACT AND HIGH-FIDELITY NOVEL VIEW SYNTHESIS
Xinhao Deng, Chaojie Zhang, Hongwei Li, Zhejiang University, China
TH4.R12.4: A DOCKER-BASED FRAMEWORK FOR PARALLEL HYPERPARAMETER TUNING OF LSTM MODELS
Anusha Srirenganathan Malarvizhi, George Mason University, United States; Tayven Stover, Northern Virginia Community College, United States; Seren Smith, George Mason University, United States; Kaylee Smith, University of Michigan, United States; Zifu Wang, Harvard University, United States; Chaowei Yang, George Mason University, United States
Contacts