HyperPower: Power- and memory-constrained hyper-parameter optimization for neural networks
Authors:
- Dimitrios StamoulisDSDimitrios Stamoulis
- Ermao CaiECErmao Cai
- Da-Cheng JuanDJDa-Cheng Juan
- Diana MarculescuDMDiana Marculescu
- 1 March 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 19-24
Abstract
No abstract availableAll Related Versions
This publication has 7 references indexed in Scilit:
- A case for efficient accelerator design space exploration via Bayesian optimization2017
- Neural networks designing neural networks2016
- Exploring aging deceleration in FinFET-based multi-core systems2016
- DeLight2016
- Can We Guarantee Performance Requirements under Workload and Process Variations?2016
- Taking the Human Out of the Loop: A Review of Bayesian OptimizationProceedings of the IEEE, 2015
- Efficient Reliability Analysis of Processor Datapath using Atomistic BTI Variability Models2015