Statistical-Mechanical Analysis of Pre-training and Fine Tuning in Deep Learning

Abstract

In this paper, we present a statistical-mechanical analysis of deep learning. We elucidate some of the essential components of deep learning---pre-training by unsupervised learning and fine tuning by supervised learning. We formulate the extraction of features from the training data as a margin criterion in a high-dimensional feature-vector space. The self-organized classifier is then supplied with small amounts of labelled data, as in deep learning. Although we employ a simple single-layer perceptron model, rather than directly analyzing a multi-layer neural network, we find a nontrivial phase transition that is dependent on the number of unlabelled data in the generalization error of the resultant classifier. In this sense, we evaluate the efficacy of the unsupervised learning component of deep learning. The analysis is performed by the replica method, which is a sophisticated tool in statistical mechanics. We validate our result in the manner of deep learning, using a simple iterative algorithm to learn the weight vector on the basis of belief propagation.

Cite this paper

@article{ohzeki2015statistical,
  title = {{Statistical-Mechanical Analysis of Pre-training and Fine Tuning in Deep Learning}},
  author = {Ohzeki, Masayuki},
  journal = {Journal of the Physical Society of Japan},
  volume = {84},
  number = {3},
  pages = {034003},
  year = {2015},
  doi = {10.7566/jpsj.84.034003}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers