English

PCA-Initialized Deep Neural Networks Applied To Document Image Analysis

Machine Learning 2018-04-25 v1 Machine Learning

Abstract

In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encoder, and 3) re-use of layers from another network (transfer learning). Therefore, typically, many training epochs are needed before meaningful weights are learned, or a rather similar dataset is required for seeding a fine-tuning of transfer learning. In this paper, we describe how to turn a PCA into an auto-encoder, by generating an encoder layer of the PCA parameters and furthermore adding a decoding layer. We analyze the initialization technique on real documents. First, we show that a PCA-based initialization is quick and leads to a very stable initialization. Furthermore, for the task of layout analysis we investigate the effectiveness of PCA-based initialization and show that it outperforms state-of-the-art random weight initialization methods.

Keywords

Cite

@article{arxiv.1702.00177,
  title  = {PCA-Initialized Deep Neural Networks Applied To Document Image Analysis},
  author = {Mathias Seuret and Michele Alberti and Rolf Ingold and Marcus Liwicki},
  journal= {arXiv preprint arXiv:1702.00177},
  year   = {2018}
}
R2 v1 2026-06-22T18:06:18.318Z