Hyper-parameter optimization of deep convolutional networks for object recognition
- Resource Type
- Conference
- Authors
- Talathi, Sachin S.
- Source
- 2015 IEEE International Conference on Image Processing (ICIP) Image Processing (ICIP), 2015 IEEE International Conference on. :3982-3986 Sep, 2015
- Subject
- Computing and Processing
Signal Processing and Analysis
Optimization
Training
Benchmark testing
Convolution
Object recognition
Neurons
Databases
hyper-parameter optimization
deep convolution networks
sequential model based optimization
- Language
Recently sequential model based optimization (SMBO) has emerged as a promising hyper-parameter optimization strategy in machine learning. In this work, we investigate SMBO to identify architecture hyper-parameters of deep convolution networks (DCNs) object recognition. We propose a simple SMBO strategy that starts from a set of random initial DCN architectures to generate new architectures, which on training perform well on a given dataset. Using the proposed SMBO strategy we are able to identify a number of DCN architectures that produce results that are comparable to state-of-the-art results on object recognition benchmarks.