Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Passive-Aggressive online learning with nonlinear embeddings

  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Paredes Palacios, Roberto
[EN] Nowadays, there is an increasing demand for machine learning techniques which can deal with problems where the instances are produced as a stream or in real time. In these scenarios, online learning is able to learn a model from data that comes continuously. The adaptability, efficiency and scalability of online learning techniques have been gaining interest last years with the increasing amount of data generated every day. In this paper, we propose a novel binary classification approach based on nonlinear mapping functions under an online learning framework. The non-convex optimization problem that arises is split into three different convex problems that are solved by means of Passive-Aggressive Online Learning. We evaluate both the adaptability and generalization of our model through several experiments comparing with the state of the art techniques. We improve significantly the results in several datasets widely used previously by the online learning community. (C) 2018 Elsevier Ltd. All rights reserved., This work was developed in the framework of the PROM-ETEOII/2014/030 research project "Adaptive learning and multi modality in machine translation and text transcription", funded by the Generalitat Valenciana. The work of the first author is financed by Grant FPU14/03981, from the Spanish Ministry of Education, Culture and Sport.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Empirical Evaluation of Variational Autoencoders for Data Augmentation

  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Paredes Palacios, Roberto
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Vieco Pérez, Jesús
  • Benedí Ruiz, José Miguel
Since the beginning of Neural Networks, different mechanisms have been required to provide a sufficient number of examples to avoid overfitting. Data augmentation, the most common one, is focused on the generation of new instances performing different distortions in the real samples. Usually, these transformations are problem-dependent, and they result in a synthetic set of, likely, unseen examples. In this work, we have studied a generative model, based on the paradigm of encoder-decoder, that works directly in the data space, that is, with images. This model encodes the input in a latent space where different transformations will be applied. After completing this, we can reconstruct the latent vectors to get new samples. We have analysed various procedures according to the distortions that we could carry out, as well as the effectiveness of this process to improve the accuracy of different classification systems. To do this, we could use both the latent space and the original space after reconstructing the altered version of these vectors. Our results have shown that using this pipeline (encoding-altering-decoding) helps the generalisation of the classifiers that have been selected., This work was developed in the framework of the PROMETEOII/2014/030 research project "Adaptive learning and multimodality in machine translation and text transcription", funded by the Generalitat Valenciana. The work of the first author is financed by Grant FPU14/03981, from the Spanish Ministry of Education, Culture and Sport.