Conference proceeding
Evolving deep autoencoders
Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, pp.123-124
GECCO '20
07/08/2020
DOI: 10.1145/3377929.3390011
Abstract
Autoencoders have seen wide success in domains ranging from feature selection to information retrieval. Despite this success, designing an autoencoder for a given task remains a challenging undertaking due to the lack of firm intuition on how the backing neural network architectures of the encoder and decoder impact the overall performance of the autoencoder. In this work we present a distributed system that uses an efficient evolutionary algorithm to design a modular autoencoder. We demonstrate the effectiveness of this system on the tasks of manifold learning and image denoising. The system beats random search by nearly an order of magnitude on both tasks while achieving near linear horizontal scaling as additional worker nodes are added to the system.
Details
- Title: Subtitle
- Evolving deep autoencoders
- Creators
- Jeff Hajewski - Salesforce (United States)Suely Oliveira - University of IowaXiaoyu Xing - Amazon (United States)
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, pp.123-124
- Series
- GECCO '20
- DOI
- 10.1145/3377929.3390011
- Publisher
- ACM
- Language
- English
- Date published
- 07/08/2020
- Academic Unit
- Computer Science; Mathematics
- Record Identifier
- 9984259476402771
Metrics
20 Record Views