A carregar...
Projeto de investigação
Center of Mathematics of the University of Minho
Financiador
Autores
Publicações
Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets
Publication . Spolaôr, Newton; Lee, Huei Diana; Mendes, Ana Isabel; Nogueira, Conceição; Parmezan, Antonio Rafael Sabino; Takaki, Weber Shoity Resende; Coy, Claudio Saddy Rodrigues; Wu, Feng Chung; Fonseca-Pinto, Rui
Convolutional neural networks have been effective in several applications, arising as a promising supporting tool in a relevant Dermatology problem: skin cancer diagnosis. However, generalizing well can be difficult when little training data is available. The fine-tuning transfer learning strategy has been employed to differentiate properly malignant from non-malignant lesions in dermoscopic images. Fine-tuning a pre-trained network allows one to classify data in the target domain, occasionally with few images, using knowledge acquired in another domain. This work proposes eight fine-tuning settings based on convolutional networks previously trained on ImageNet that can be employed mainly in limited data samples to reduce overfitting risk. They differ on the architecture, the learning rate and the number of unfrozen layer blocks. We evaluated the settings in two public datasets with 104 and 200 dermoscopic images. By finding competitive configurations in small datasets, this paper illustrates that deep learning can be effective if one has only a few dozen malignant and non-malignant lesion images to study and differentiate in Dermatology. The proposal is also flexible and potentially useful for other domains. In fact, it performed satisfactorily in an assessment conducted in a larger dataset with 746 computerized tomographic images associated with the coronavirus disease.
The word problem for κ-terms over the pseudovariety of local groups
Publication . Costa, J. C.; Nogueira, C.; Teixeira, M. L.
In this paper we study the κ-word problem for the pseudovariety LG of local groups, where κ is the canonical signature consisting of the multiplication and the pseudoinversion. We solve this problem by transforming each arbitrary κ-term α into another one α∗ called the LG-canonical form of α and by showing that different canonical forms have different interpretations over LG. The procedure of construction of these canonical forms consists in applying reductions determined by a set Σ of κ-identities. As a consequence, Σ is a basis of κ-identities for the κ-variety generated by LG.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
6817 - DCRRNI ID
Número da atribuição
UIDP/00013/2020