Random search and reproducibility for neural architecture search /

"Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. Ameet Talwalkar (Carnegie Mellon University | Determined AI) shares work that aims to help ground the empirical results in th...

Full description

Bibliographic Details
Call Number:Libro Electrónico
Corporate Author: O'Reilly Artificial Intelligence Conference
Format: Electronic Conference Proceeding Video
Language:Inglés
Published: [Place of publication not identified] : O'Reilly, 2019.
Subjects:
Neural networks (Computer science)
Machine learning.
Computer network architectures.
Neural Networks, Computer
Réseaux neuronaux (Informatique)
Apprentissage automatique.
Réseaux d'ordinateurs > Architectures.
Online Access:Texto completo (Requiere registro previo con correo institucional)
Description
Summary:"Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. Ameet Talwalkar (Carnegie Mellon University | Determined AI) shares work that aims to help ground the empirical results in this field and proposes new NAS baselines that build off the following observations: NAS is a specialized hyperparameter optimization problem, and random search is a competitive baseline for hyperparameter optimization. Leveraging these observations, Ameet evaluates both random search with early-stopping and a novel random search with a weight-sharing algorithm on two standard NAS benchmarks: PTB and CIFAR-10. Results show that random search with early-stopping is a competitive NAS baseline that performs at least as well as ENAS, a leading NAS method, on both benchmarks. Additionally, random search with weight-sharing outperforms random search with early-stopping, achieving a state-of-the-art NAS result on PTB and a highly competitive result on CIFAR-10. Ameet concludes by exploring existing reproducibility issues for published NAS results, noting the lack of source material needed to exactly reproduce these results, and discussing the robustness of published results given the various sources of variability in NAS experimental setups."--Resource description page
Item Description:Title from title screen (viewed November 14, 2019).
Physical Description:1 online resource (1 streaming video file (40 min., 46 sec.))

Similar Items