Conference proceeding
Efficient Evolution of Variational Autoencoders
2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC), pp.1541-1550
01/27/2021
DOI: 10.1109/CCWC51732.2021.9376167
Abstract
Despite the extensive successes of deep learning, designing effective neural networks remains an unsolved challenge in deep learning. The complexity of interactions between all the network hyperparameters such as activation type, layer size, number of layers, and connection patterns is far beyond current understanding. As a result, designing an effective neural network can be as much art as it is science. To that end, neural architecture search aims to automate the task of network design; however, many neural architecture search systems are not feasible for the typical research institution due to the high cost of operation. In this work we propose two simple techniques that have a dramatic impact on search cost, achieving as much as a 900% speed-up in per generation training time, with minimal impact on the efficacy of the search algorithm. Similarly, we achieve a 50% reduction in search time without sacrificing any performance.
Details
- Title: Subtitle
- Efficient Evolution of Variational Autoencoders
- Creators
- Jeff Hajewski - Salesforce (United States)Suely Oliveira - University of Iowa
- Resource Type
- Conference proceeding
- Publication Details
- 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC), pp.1541-1550
- DOI
- 10.1109/CCWC51732.2021.9376167
- Publisher
- IEEE
- Language
- English
- Date published
- 01/27/2021
- Academic Unit
- Computer Science; Mathematics
- Record Identifier
- 9984259486002771
Metrics
16 Record Views