default search action
OpML 2020
- Nisha Talagala, Joel Young:
2020 USENIX Conference on Operational Machine Learning, OpML 2020, July 28 - August 7, 2020. USENIX Association 2020
Session 1: Deep Learning and GPU Accelerated Data Science
- Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-mei W. Hwu:
DLSpec: A Deep Learning Task Exchange Specification.
Session 2: Model Life Cycle
- Chandra Mohan Meena, Sarwesh Suman, Vijay Agneeswaran:
Finding Bottleneck in Machine Learning Model Life Cycle.
Session 3: Features, Explainability, and Analytics
- Fabio Casati, Veeru Metha, Gopal Sarda, Sagar Davasam, Kannan Govindarajan:
Detecting Feature Eligibility Illusions in Enterprise AI Autopilots. - Alexandru A. Ormenisan, Moritz Meister, Fabio Buso, Robin Andersson, Seif Haridi, Jim Dowling:
Time Travel and Provenance for Machine Learning Pipelines. - Thomas Rausch, Waldemar Hummer, Vinod Muthusamy:
An Experimentation and Analytics Framework for Large-Scale AI Operations Platforms. - Lisa Veiber, Kevin Allix, Yusuf Arslan, Tegawendé F. Bissyandé, Jacques Klein:
Challenges Towards Production-Ready Explainable Machine Learning.
Session 4: Algorithms
- Jiawen Liu, Zhen Xie, Dimitrios S. Nikolopoulos, Dong Li:
RIANN: Real-time Incremental Learning with Approximate Nearest Neighbor on Mobile Devices.
Session 5: Model Deployment Strategies
- Edward Verenich, Alvaro Velasquez, M. G. Sarwar Murshed, Faraz Hussain:
FlexServe: Deployment of PyTorch Models as Flexible REST Endpoints.
Session 6: Applications and Experiences
- Shunya Ueta, Suganprabu Nagaraja, Mizuki Sango:
Auto Content Moderation in C2C e-Commerce. - Amitabha Banerjee, Chien-Chia Chen, Chien-Chun Hung, Xiaobo Huang, Yifan Wang, Razvan Chevesaran:
Challenges and Experiences with MLOps for Performance Diagnostics in Hybrid-Cloud Enterprise Software Deployments.
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.