Results 231 to 240 of about 98,022 (269)
Some of the next articles are maybe not open access.
Sequential Model-Free Hyperparameter Tuning
2015 IEEE International Conference on Data Mining, 2015Hyperparameter tuning is often done manually but current research has proven that automatic tuning yields effective hyperparameter configurations even faster and does not require any expertise. To further improve the search, recent publications propose transferring knowledge from previous experiments to new experiments.
Martin Wistuba +2 more
openaire +1 more source
Hyperparameter Tuning of ConvLSTM Network Models
2021 44th International Conference on Telecommunications and Signal Processing (TSP), 2021Deep learning algorithms have achieved amazing performance in computer vision area. However, a biggest problem deep learning has, is the high dependency on hyper-parameters. The algorithm results may be different, depending on hyper-parameters. This paper presents an effective method for hyper-parameter tuning using deep learning.
Roberta Vrskova +4 more
openaire +1 more source
No More Pesky Hyperparameters: Offline Hyperparameter Tuning For Reinforcement Learning
2021The performance of reinforcement learning (RL) agents is sensitive to the choice of hyperparameters. In real-world settings like robotics or industrial control systems, however, testing different hyperparameter configurations directly on the environment can be financially prohibitive, dangerous, or time consuming.
openaire +1 more source
Tuning SVM hyperparameters in the primal
2010 Second International Conference on Computational Intelligence and Natural Computing, 2010Choosing optimal hyperparameters for Support Vector Machines(SVMs) is quite difficult but extremely essential in SVM design. This is usually done by minimizing estimates of generalization error such as the k-fold cross-validation error or the upper bound of leave-one-out(LOO) error.
null Huang Dongyuan, null Chen Xiaoyun
openaire +1 more source
Hyperparameter Tuning using Quantum Genetic Algorithms
2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019Correctly tuning the hyperparameters of a machine learning model can improve classification results. Typically hyperparameter tuning is made by humans and experience is needed to fine tune them. Algorithmic approaches have been extensively studied in the literature and can find better results.
Athanasios Lentzas +2 more
openaire +1 more source
Game AI hyperparameter tuning in rinascimento
Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2019Hyperparameter tuning is an important mixed-integer optimisation problem, especially in the context of real-world applications such as games. In this paper, we propose a function suite around hyperparameter optimisation of game AI based on the card game Splendor and using the Rinascimento framework.
Ivan Bravi, Vanessa Volz, Simon Lucas
openaire +1 more source
An Approach to Tuning Hyperparameters in Parallel: An Approach to Tuning Hyperparameters in Parallel
2019Predicting violent storms and dangerous weather conditions, for instance predicting tornados, is an important application for public safety. Using numerical weather simulations to classify a weather pattern as tornadic or not tornadic can take a long time due to the immense complexity associated with current models.
openaire +1 more source
Grid search hyperparameter tuning in additive manufacturing processes
Manufacturing Letters, 2023Salil Desai
exaly