10 documents found, page 1 of 1
Differentiable weightless neural networks
Bacellar, A.; Susskind, Z.; Breternitz Jr., M.; John, E.; John, L.; Lima, P.; França, F.We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We propose Learnable Mapping, Learnable Reduction, and Spectral Regularization to further improve the accuracy and efficiency of these models. We evaluate DWNs in three edge co...
Gluten-free diet among Portuguese coeliac adults: perceived difficulties
Lima, P.; Silva, S.; Tavares, G.; Poínhos, Rui; Silva, Diana
Benefits of condylar distraction in patients with temporomandibular dysfunction
Castro, R.; Lima, P.; Fernandes, M.; Martinho, J.; Moleirinho-Alves, P.; Pereira, A. M.
Lisbon’s womb: an approach to the city metabolism in the turn to the twentieth ...
Niza, S.; Ferreira, D.; Mourão, J.; Lima, P.; Marat-Mendes, T.The consumption and production of food products in the municipality of Lisbon in the 1890–1900 decade is assessed with the support of historical cartography and statistical resources. For the first time, food production in a municipality in the turn to the twentieth century is accounted and simultaneously subject of a visual analysis of the land used for agriculture and of the water infrastructures that support...
Água corrente (não) mata gente: caracterização do abastecimento de água, salubr...
Marat-Mendes, T.; Mourão, J.; Lima, P.; Niza, S.O presente artigo promove uma análise das sedes de concelho no território correspondente à atual Área Metropolitana da Lisboa (AML) em 1940. As condições de abastecimento de água, saneamento e salubridade, cultivos e alimentação são analisadas para dezasseis sedes de concelho. É objetivo deste estudo promover uma caracterização visual detalhada dos elementos relacionados com a agricultura (usos do solo) e com a...
To err is robotic, to tolerate immunological: fault detection in multirobot sys...
Tarapore, D.; Lima, P.; Carneiro, J.; Christensen, A. L.Fault detection and fault tolerance represent two of the most important and largely unsolved issues in the field of multirobot systems (MRS). Efficient, long-term operation requires an accurate, timely detection, and accommodation of abnormally behaving robots. Most existing approaches to fault-tolerance prescribe a characterization of normal robot behaviours, and train a model to recognize these behaviours. Be...
Tribocorrosion behavior of Ti–C–O–N nanostructured thin films (black) for decor...
Lima, P.; Araújo, M.; Mathew, M. T.; Rocha, L. A.; Pinto, A. M. P.; Chappé, J. M.; Ramos, Marta M. D.; Marques, L.; Pierson, J. F.; Vaz, F.In the past few years, tribocorrosion has become a focus of research because of its relevance in terms of the future in-service degradation mechanisms of materials. In the particular case of decorative coatings, tribocorrosion is certainly one of the most important issues, and sweat corrosion and human contact wear are two other factors that may act as material selection tools. Thus, the current study aimed to ...
Optical fiber relative humidity sensor based on a FBG with a di-ureasil coating
Correia, S.; Antunes, P.; Pecoraro, E.; Lima, P.; Varum, H.; Carlos, L. D.; Ferreira, R.; André, P.In this work we proposed a relative humidity (RH) sensor based on a Bragg grating written in an optical fiber, associated with a coating of organo-silica hybrid material prepared by the sol-gel method. The organo-silica-based coating has a strong adhesion to the optical fiber and its expansion is reversibly affected by the change in the RH values (15.0–95.0%) of the surrounding environment, allowing an increase...
Prediction of dynamic plasmid production by recombinant escherichia coli fed-ba...
Silva, T.; Lima, P.; Roxo-Rosa, M.; Hageman, S.; Fonseca, L. P.; Calado, C. R. C.A generalized regression neural network with external feedback was used to predict plasmid production in a fed-batch cultivation of recombinant Escherichia coli. The neu ral network was built out of the experimental data obtained on a few cultivations, of which the general strategy was based on an initial batch phase followed by an exponen tial feeding phase. The different cultivation conditions used resulted i...
Prediction of dynamic plasmid production by recombinant escherichia coli fed-ba...
Silva, T.; Lima, P.; Roxo-Rosa, M.; Hageman, S.; Fonseca, L. P.; Calado, CecíliaA generalized regression neural network with external feedback was used to predict plasmid production in a fed-batch cultivation of recombinant Escherichia coli. The neural network was built out of the experimental data obtained on a few cultivations, of which the general strategy was based on an initial batch phase followed by an exponential feeding phase. The different cultivation conditions used resulted in ...