Abstract
Designing deep neural networks by human engineers can be challenging because there are various choices of deep neural network structures. We developed a deep neuroevolution system to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using a probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. Our approach takes advantage of the probabilistic dependencies found among the structures of networks. The system was applied to tackle the problem of the physiological signal classification of abnormal heart rhythm. In the classification problem, our discovered model is more accurate than AlexNet. Our discovered model uses about 2% of the total amount of parameters of AlexNet.
| Original language | English |
|---|---|
| Title of host publication | GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion |
| Place of Publication | New York |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 87-88 |
| Number of pages | 2 |
| ISBN (Electronic) | 9781450367486 |
| ISBN (Print) | 9781450367486 |
| DOIs | |
| Publication status | Published - 13 Jul 2019 |
| Event | 2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, Czech Republic Duration: 13 Jul 2019 → 17 Jul 2019 |
Publication series
| Name | GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion |
|---|
Conference
| Conference | 2019 Genetic and Evolutionary Computation Conference, GECCO 2019 |
|---|---|
| Abbreviated title | GECCO 19 |
| Country/Territory | Czech Republic |
| City | Prague |
| Period | 13/07/19 → 17/07/19 |
Funding
This research is supported by the Institute of Future Cities of The Chinese University of Hong Kong.
Keywords
- Estimation of Distribution Programming
- Deep Neural Network