Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
About

About

Graduated from the Integrated Master in Informatics and Computing Engineering at the Faculty of Engineering of the University of Porto - FEUP. You can find my MSc dissertation by clicking here! I love technology and innovation ever since I was a little girl. I have special interest in the areas of Data Science and Machine Learning, Databases and Web Development. Besides Informatics, I'm also passionate about mathematics, philosophy, biology, sports, traveling and photography.

Interest
Topics
Details

Details

001
Publications

2018

Autoencoders as Weight Initialization of Deep Classification Networks Applied to Papillary Thyroid Carcinoma

Authors
Ferreira, MF; Camacho, R; Teixeira, LF;

Publication
PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)

Abstract
Cancer is one of the most serious health problems of our time. One approach for automatically classifying tumor samples is to analyze derived molecular information. Previous work by Teixeira et al. compared different methods of Data Oversampling and Feature Reduction, as well as Deep (Stacked) Denoising Autoencoders followed by a shallow layer for classification. In this work, we compare the performance of 6 different types of Autoencoder (AE), combined with two different approaches when training the classification model: (a) fixing the weights, after pretraining an AE, and (b) allowing fine-tuning of the entire network. We also apply two different strategies for embedding the AE into the classification network: (1) by only importing the encoding layers, and (2) by importing the complete AE. Our best result was the combination of unsupervised feature learning through a single-layer Denoising AE, followed by its complete import into the classification network, and subsequent fine-tuning through supervised training, achieving an F1 score of 99.61% +/- 0.54. We conclude that a reconstruction of the input space, combined with a deeper classification network outperforms previous work, without resorting to data augmentation techniques.