CV Lattes
ORCID
Google Scholar Citations
Universidade Estadual de Campinas (UNICAMP). Instituto de Computação (IC) (Institutional affiliation from the last research proposal) Birthplace: Brazil
Barbara is graduated in Bachelor of Information Systems from Universidade Estadual Paulista - FC / Bauru (2017) and held his Scientific Initiation and research internship at Harvard University and Middlesex University. She has her Master Degree in Computer Science from the State University of Campinas (2019) and research internship at Groningen University. She is currently a doctoral student in Computer Science at the State University of Campinas under cotutelle with Utrecht University and researcher in the Laboratory of Image Data Science (LIDS) since 2019.She has experience in Computer Science, focusing on machine learning and visual data analysis, specializing in artificial neural networks, deep learning, dimensionality reduction and data visualization. (Source: Lattes Curriculum)
| News published in Agência FAPESP Newsletter about the researcher |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |
Machine Learning models can be very effective when the number of labeled training samples is high. In some areas, such as Medicine and Biology, large labeled training sets are very difficult to be obtained, given that the manual annotation of such datasets is time-consuming and requires specialists. In general, data annotation based on the visual inspection (supervision) of each training …
Artificial Neural Networks, specifically those with a deep architecture (with more than two hidden layers), are usually affected by an occurrence known as super-training of data. In the super-training of data, the premature convergence of the network generates quite satisfactory results in the training and validation sets, but with a lower performance expected on the test set. Among the m…
Convolutional Neural Networks (CNN) have been extensively employed in the last years as an alternative to the traditional methods of feature extraction. Their methodology is based on the hierarchical processing of human brain, and they have obtained good results for image classification tasks, since they are invariant to changes in scale and rotation. However, a big issue of such approach…
Deep neural networks can be very effective for image classification. However, they usually rely on large supervised training sets to reduce/avoid high classification accuracy on the training data with low accuracy on unseen test sets --- a phenomenon known as \emph{data overfitting}. Large supervised (labeled) training sets are usually impractical in applications that require human expert…
Deep neural networks can be very effective for image classification, but they usually rely on regularization methods, transfer learning, and/or large supervised training sets to reduce/avoid high classification accuracy on the training data with low accuracy on unseen test sets --- i.e., a phenomenon known as data overfitting. Transfer learning is not always possible and large supervised …
The problem of fine-tuning parameters in deep learning techniques has been considerably focused in the last years, since to hand-tune them is painful and prone to errors. In this proposal, we model the problem of adjusting parameters as an optimization task, since meta- heuristic techniques have obtained very interesting results in a number of problems. There is one inspired on the behavi…
(Only some records are available in English at this moment)
| 3 / 3 | Completed scholarships in Brazil |
| 4 / 4 | Completed scholarships abroad |
| 7 / 7 | All Scholarships |
| Associated processes | |