Publication:4633077
From MaRDI portal
zbMath1485.68229arXiv1808.05377MaRDI QIDQ4633077
Jan Hendrik Metzen, Frank Hutter, Thomas Elsken
Publication date: 2 May 2019
Full work available at URL: https://arxiv.org/abs/1808.05377
search strategy; neural architecture search; AutoDL; AutoML; performance estimation strategy; search space design
68T07: Artificial neural networks and deep learning
68-02: Research exposition (monographs, survey articles) pertaining to computer science
68T20: Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)
Related Items
Unnamed Item, Unnamed Item, Unnamed Item, A Comprehensive Review of Modern Object Segmentation Approaches, Personalized Algorithm Generation: A Case Study in Learning ODE Integrators, Automated Reinforcement Learning (AutoRL): A Survey and Open Problems, An Image-Based Approach to Detecting Structural Similarity Among Mixed Integer Programs, Derivation and Analysis of Fast Bilinear Algorithms for Convolution, Quantifying the separability of data classes in neural networks, Reconstruction of proper numerical inlet boundary conditions for draft tube flow simulations using machine learning, Satellite derived bathymetry using deep learning, gLaSDI: parametric physics-informed greedy latent space dynamics identification, \textit{FastSVD-ML-ROM}: a reduced-order modeling framework based on machine learning for real-time applications, Editorial: special issue on recent progress in autonomous machine learning, AutonoML: Towards an Integrated Framework for Autonomous Machine Learning, Automated Deep Learning: Neural Architecture Search Is Not the End, A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms, Goal-oriented sensitivity analysis of hyperparameters in deep learning, Learning optimal solutions via an LSTM-optimization framework, Neural architecture search via standard machine learning methodologies, A tight upper bound on the generalization error of feedforward neural networks, Sequential model based optimization of partially defined functions under unknown constraints, Optimization problems for machine learning: a survey, Negotiating team formation using deep reinforcement learning, Harnessing the power of deception in attack graph-based security games, Use of static surrogates in hyperparameter optimization, Symbolic DNN-tuner, Physics-informed neural networks for solving forward and inverse flow problems via the Boltzmann-BGK formulation, Self-adaptive deep neural network: numerical approximation to functions and PDEs, How can machine learning and optimization help each other better?, A fast multi-fidelity method with uncertainty quantification for complex data correlations: application to vortex-induced vibrations of marine risers, A survey on semi-supervised learning, Multi-objective evolutionary algorithms are generally good: maximizing monotone submodular functions over sequences, Spatial steganalysis based on gradient-based neural architecture search
Cites Work
- Unnamed Item
- Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
- Fast Bayesian hyperparameter optimization on large datasets
- Simple statistical gradient-following algorithms for connectionist reinforcement learning
- Modularized Morphing of Deep Convolutional Neural Networks: A Graph Approach
- An Introduction to Variational Autoencoders
