English

Hyper-parameter optimization of Deep Convolutional Networks for object recognition

Computer Vision and Pattern Recognition 2015-05-19 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1501.07645,
  title  = {Hyper-parameter optimization of Deep Convolutional Networks for object recognition},
  author = {Sachin S. Talathi},
  journal= {arXiv preprint arXiv:1501.07645},
  year   = {2015}
}

Comments

4 pages, 1 figure, 3 tables, Submitted to ICIP 2015

R2 v1 2026-06-22T08:16:17.528Z