VISUALHYPERTUNER: VISUAL ANALYTICS FOR USER-DRIVEN HYPERPARAMTER TUNING OF DEEP NEURAL NETWORKS
暂无分享,去创建一个
Jaegul Choo | Minkyu Kim | Heungseok Park | Nako Sung | Ji-Hoon Kim | Jung-Woo Ha | Jung-Woo Ha | J. Choo | Minkyu Kim | Ji-Hoon Kim | Jinwoong Kim | Nako Sung | Jinwoong Kim | Heungseok Park
[1] Yi Yang,et al. Random Erasing Data Augmentation , 2017, AAAI.
[2] A. Inselberg,et al. Parallel coordinates for visualizing multi-dimensional geometry , 1987 .
[3] Jung-Woo Ha,et al. NSML: Meet the MLaaS platform with a real-world case study , 2018, ArXiv.
[4] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[5] Ameet Talwalkar,et al. Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization , 2016, J. Mach. Learn. Res..
[6] Ion Stoica,et al. Tune: A Research Platform for Distributed Model Selection and Training , 2018, ArXiv.
[7] Jung-Woo Ha,et al. CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms , 2018, ArXiv.
[8] Peter Henderson,et al. Oríon : Experiment Version Control for Efficient Hyperparameter Optimization , 2018 .
[9] D. Sculley,et al. Google Vizier: A Service for Black-Box Optimization , 2017, KDD.
[10] Max Jaderberg,et al. Population Based Training of Neural Networks , 2017, ArXiv.