Sherpa: Robust hyperparameter optimization for machine learning
Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks. With Sherpa, scientists can quickly optimize hyperparameter...
Main Authors: | Lars Hertel, Julian Collado, Peter Sadowski, Jordan Ott, Pierre Baldi |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-07-01
|
Series: | SoftwareX |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352711020303046 |
Similar Items
-
Streamlining hyperparameter optimization for radiation emulator training with automated Sherpa
by: Soonyoung Roh, et al.
Published: (2024-04-01) -
Prediction of concrete compressive strength using deep neural networks based on hyperparameter optimization
by: Mohammed Naved, et al.
Published: (2024-12-01) -
Improving the Robustness and Quality of Biomedical CNN Models through Adaptive Hyperparameter Tuning
by: Saeed Iqbal, et al.
Published: (2022-11-01) -
Hyperparameter Optimization Using Iterative Decision Tree (IDT)
by: Narith Saum, et al.
Published: (2022-01-01) -
A Population-Based Hybrid Approach for Hyperparameter Optimization of Neural Networks
by: Luis Japa, et al.
Published: (2023-01-01)