Publication Type:

Journal Article

Source:

Journal of Intelligent and Fuzzy Systems, IOS Press, Volume 36, Number 3, p.1987-1995 (2019)

URL:

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063506820&doi=10.3233%2fJIFS-169910&partnerID=40&md5=98d2280bd66fc858d6f89ad2d85f4aad

Keywords:

Auto encoders, Biomedical informatics, Convolution, Deep learning, Deep neural networks, Dimensionality reduction, Intelligent systems, NAtural language processing, Natural language processing systems, Optimum model, Small scale, Soft computing, Training strategy, Training time

Abstract:

Deep neural networks have dramatically gained immense potential in almost every field like computer vision, natural language processing, biomedical informatics etc. Among these networks, autoencoders are popular in performing dimensionality reduction task, while learning a representation for an unlabeled dataset. A usual way of dealing with such networks is to pre-train them in a layer-wise fashion, and consequently fine-tune the whole stack in a supervised manner. In this paper, a pair-wise training strategy is proposed to determine optimum model parameters by reducing training time as well as the complexity of training a convolutional autoencoder without compromising its accuracy. The proposed approach works in a fully unsupervised manner and has been tested on datasets like MNIST, CIFAR10, and CIFAR100 and it shows that the training time has improved by an average of 25% on these three datasets. © 2019 - IOS Press and the authors.

Cite this Research Publication

A. S. Kumar and Jyothisha J. Nair, “Pair wise training for stacked convolutional autoencoders using small scale images”, Journal of Intelligent and Fuzzy Systems, vol. 36, pp. 1987-1995, 2019.