40 citations · 42 across the 5 of their papers we have counts for
5 papers · 1 filter
Iterative Pseudo-Labeling with Deep Feature Annotation and Confidence-Based Sampling
Barbara C Benato, Alexandru C Telea, Alexandre X Falcão
Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-…
HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
Gabriel Appleby, Mateus Espadoto, Rui Chen +4
Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, i…
Semi-Automatic Data Annotation guided by Feature Space Projection
Barbara Caroline Benato, Jancarlo Ferreira Gomes, Alexandru Cristian Telea +1
Data annotation using visual inspection (supervision) of each training sample can be laborious. Interactive solutions alleviate this by helping experts propagate labels from a few…
Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling
Lucas Pagliosa, Alexandru Telea, Rodrigo Mello
The reconstruction of phase spaces is an essential step to analyze time series according to Dynamical System concepts. A regression performed on such spaces unveils the relationshi…
Deep Learning Multidimensional Projections
Mateus Espadoto, Nina S. T. Hirata, Alexandru C. Telea
Dimensionality reduction methods, also known as projections, are frequently used for exploring multidimensional data in machine learning, data science, and information visualizatio…