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
Interest
Topics
Details

Details

  • Name

    Catarina Félix Oliveira
  • Cluster

    Computer Science
  • Role

    External Student
  • Since

    01st December 2008
001
Publications

2018

Using metalearning for parameter tuning in neural networks

Authors
Felix, C; Soares, C; Jorge, A; Ferreira, H;

Publication
Lecture Notes in Computational Vision and Biomechanics

Abstract
Neural networks have been applied as a machine learning tool in many different areas. Recently, they have gained increased attention with what is now called deep learning. Neural networks algorithms have several parameters that need to be tuned in order to maximize performance. The definition of these parameters can be a difficult, extensive and time consuming task, even for expert users. One approach that has been successfully used for algorithm and parameter selection is metalearning. Metalearning consists in using machine learning algorithm on (meta)data from machine learning experiments to map the characteristics of the data with the performance of the algorithms. In this paper we study how a metalearning approach can be used to obtain a good set of parameters to learn a neural network for a given new dataset. Our results indicate that with metalearning we can successfully learn classifiers from past learning tasks that are able to define appropriate parameters. © 2018, Springer International Publishing AG.

2016

Can Metalearning Be Applied to Transfer on Heterogeneous Datasets?

Authors
Felix, C; Soares, C; Jorge, A;

Publication
Hybrid Artificial Intelligent Systems

Abstract
Machine learning processes consist in collecting data, obtaining a model and applying it to a given task. Given a new task, the standard approach is to restart the learning process and obtain a new model. However, previous learning experience can be exploited to assist the new learning process. The two most studied approaches for this are meta-learning and transfer learning. Metalearning can be used for selecting the predictive model to use on a new dataset. Transfer learning allows the reuse of knowledge from previous tasks. However, when multiple heterogeneous tasks are available as potential sources for transfer, the question is which one to use. One approach to address this problem is metalearning. In this paper we investigate the feasibility of this approach. We propose a method to transfer weights from a source trained neural network to initialize a network that models a potentially very different target dataset. Our experiments with 14 datasets indicate that this method enables faster convergence without significant difference in accuracy provided that the source task is adequately chosen. This means that there is potential for applying metalearning to support transfer between heterogeneous datasets.

2015

Metalearning for multiple-domain transfer learning

Authors
Félix, C; Soares, C; Jorge, A;

Publication
CEUR Workshop Proceedings

Abstract
Machine learning processes consist in collecting data, obtaining a model and applying it to a given task. Given a new task, the standard approach is to restart the learning process and obtain a new model. However, previous learning experience can be exploited to assist the new learning process. The two most studied approaches for this are metalearning and transfer learning. Metalearning can be used for selecting the predictive model to use over a determined dataset. Transfer learning allows the reuse of knowledge from previous tasks. Our aim is to use metalearning to support transfer learning and reduce the computational cost without loss in terms of performance, as well as the user effort needed for the algorithm selection. In this paper we propose some methods for mapping the transfer of weights between neural networks to improve the performance of the target network, and describe some experiments performed in order to test our hypothesis.

2014

Monitoring Recommender Systems: A Business Intelligence Approach

Authors
Felix, C; Soares, C; Jorge, A; Vinagre, J;

Publication
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS, PART VI - ICCSA 2014

Abstract
Recommender systems (RS) are increasingly adopted by e-business, social networks and many other user-centric websites. Based on the user's previous choices or interests, a RS suggests new items in which the user might be interested. With constant changes in user behavior, the quality of a RS may decrease over time. Therefore, we need to monitor the performance of the RS, giving timely information to management, who can than manage the RS to maximize results. Our work consists in creating a monitoring platform - based on Business Intelligence (BI) and On-line Analytical Processing (OLAP) tools - that provides information about the recommender system, in order to assess its quality, the impact it has on users and their adherence to the recommendations. We present a case study with Palco Principal(1), a social network for music.

2013

POPSTAR at RepLab 2013: Name ambiguity resolution on Twitter

Authors
Saleiro, P; Rei, L; Pasquali, A; Soares, C; Teixeira, J; Pinto, F; Nozari, M; Felix, C; Strecht, P;

Publication
CEUR Workshop Proceedings

Abstract
Filtering tweets relevant to a given entity is an important task for online reputation management systems. This contributes to a reliable analysis of opinions and trends regarding a given entity. In this paper we describe our participation at the Filtering Task of RepLab 2013. The goal of the competition is to classify a tweet as relevant or not relevant to a given entity. To address this task we studied a large set of features that can be generated to describe the relationship between an entity and a tweet. We explored different learning algorithms as well as, different types of features: text, keyword similarity scores between enti-ties metadata and tweets, Freebase entity graph and Wikipedia. The test set of the competition comprises more than 90000 tweets of 61 entities of four distinct categories: automotive, banking, universities and music. Results show that our approach is able to achieve a Reliability of 0.72 and a Sensitivity of 0.45 on the test set, corresponding to an F-measure of 0.48 and an Accuracy of 0.908.