284 citations
- LG (South Korea)KR3 papers
- Seoul National UniversityKR3 papers
- Yonsei UniversityKR2 papers
- California Southern UniversityUS1 paper
- CHA University Bundang Medical CenterKR1 paper
- Instituto Tecnológico de CanariasES1 paper
- Jilin UniversityCN1 paper
- Korea Advanced Institute of Science and TechnologyKR1 paper
- Kyonggi UniversityKR1 paper
- LG AI Research (South Korea)KR1 paper
- Microsoft (United States)US1 paper
- Norwegian University of Science and TechnologyNO1 paper
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 3 cited
Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
Jiayi Liu, Samarth Tripathi, Unmesh Kurup +1
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming. In addition to the computational effort required,…
cs.CV2019
Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques
Byeongmoon Ji, Hyemin Jung, Jihyeun Yoon +2
The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliab…