Buscar
Mostrando ítems 1-10 de 34
Entropy-Based Filter Selection in CNNs Applied to Text Classification
(2020-01-01)
Filter selection in convolutional neural networks aims at finding the most important filters in a convolutional layer, with the goal of reducing computational costs and needed storage, as well as understanding the networks’ ...
Semi-automatic CNN Architectural Pruning using the Bayesian Case Model and Dimensionality Reduction Visualization
(Scitepress, 2022-01-01)
Visualization techniques have been applied to reasoning about complex machine learning models. These visual approaches aim to enhance the understanding of black-box models' decisions or guide in hyperparameters configuration, ...
Reconfigurable 3D CAD feature recognition supporting confluent n-dimensional topologies and geometric filters for prismatic and curved models
(MDPI AG, 2020-01-01)
Feature Recognition (FR) in Computer-aided Design (CAD) models is central for Design and Manufacturing. FR is a problem whose computational burden is intractable (NP-hard), given that its underlying task is the detection ...
Reconfigurable 3D CAD feature recognition supporting confluent n-dimensional topologies and geometric filters for prismatic and curved models
(MDPI AG, 2020-01-01)
Feature Recognition (FR) in Computer-aided Design (CAD) models is central for Design and Manufacturing. FR is a problem whose computational burden is intractable (NP-hard), given that its underlying task is the detection ...
Automatic slope streak detection on Mars
(2015-10-23)
An algorithm to detect slope streaks on Mars is presented in this paper. It is mainly based on morphological operators and consists of three steps: 'pre-processing' with connected operators to filter small structures and ...