Results 31 to 40 of about 1,858,266 (298)
Bayesian Optimized Echo State Network Applied to Short-Term Load Forecasting
Energies, 2020 Load forecasting impacts directly financial returns and information in electrical systems planning. A promising approach to load forecasting is the Echo State Network (ESN), a recurrent neural network for the processing of temporal dependencies.
Gabriel Trierweiler Ribeiro +4 more
doaj +1 more source
A Novel Graph Convolutional Gated Recurrent Unit Framework for Network-Based Traffic Prediction
IEEE Access, 2023 A Smart City is characterized mainly as an efficient, technologically advanced, green, and socially informed city. An intelligent transportation system (ITS) is a subset area of smart cities that enhances the safety and mobility of road vehicles.
Basharat Hussain +4 more
doaj +1 more source
RHOASo: An Early Stop Hyper-Parameter Optimization Algorithm
Mathematics, 2021 This work proposes a new algorithm for optimizing hyper-parameters of a machine learning algorithm, RHOASo, based on conditional optimization of concave asymptotic functions.
Ángel Luis Muñoz Castañeda +2 more
doaj +1 more source
Hyperparameter Optimization with Differentiable Metafeatures
CoRR, 2021 Metafeatures, or dataset characteristics, have been shown to improve the performance of hyperparameter optimization (HPO). Conventionally, metafeatures are precomputed and used to measure the similarity between datasets, leading to a better initialization of HPO models.
Hadi S. Jomaa +2 more
openaire +2 more sources
Scaling Laws for Hyperparameter Optimization
Advances in Neural Information Processing Systems 36, 2023 Accepted at NeurIPS ...
Arlind Kadra +3 more
openaire +3 more sources
Recent advances in surrogate-based optimization [PDF]
, 2009 The evaluation of aerospace designs is synonymous with the use of long running computationally intensive simulations. This fuels the desire to harness the efficiency of surrogate-based methods in aerospace design optimization.
Alexander I.J. Forrester +3 more
core +1 more source
IEEE Access, 2023 Deep Reinforcement Learning (DRL) allows agents to make decisions in a specific environment based on a reward function, without prior knowledge. Adapting hyperparameters significantly impacts the learning process and time.
Ebrahim Hamid Hasan Sumiea +6 more
doaj +1 more source
Is one hyperparameter optimizer enough? [PDF]
Proceedings of the 4th ACM SIGSOFT International Workshop on Software Analytics, 2018 Hyperparameter tuning is the black art of automatically finding a good combination of control parameters for a data miner. While widely applied in empirical Software Engineering, there has not been much discussion on which hyperparameter tuner is best for software analytics.
Huy Tu, Vivek Nair
openaire +3 more sources
Optimization of hyperparameters for SMS reconstruction [PDF]
Magnetic Resonance Imaging, 2020 Simultaneous multi-slice (SMS) imaging accelerates MRI data acquisition by exciting multiple image slices simultaneously. Overlapping slices are then separated using a mathematical model. Several parameters used in SMS reconstruction impact the quality of final images. Therefore, finding an optimal set of reconstruction parameters is critical to ensure
Muftuler, L. Tugan +7 more
openaire +3 more sources
Hyperparameter Optimization: A Spectral Approach
CoRR, 2017 We give a simple, fast algorithm for hyperparameter optimization inspired by techniques from the analysis of Boolean functions. We focus on the high-dimensional regime where the canonical example is training a neural network with a large number of hyperparameters.
Elad Hazan +2 more
openaire +4 more sources