Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/95693
Título: | A Study on Angular Softmax | Autor: | Ul Rahman, Jamshaid | Orientador: | Chen, Qing Yang, Zhouwang |
Palavras-chave: | Additive Parameter; Angular Margin; Deep Convolutional Neural Networks; Image Recognition; Softmax Loss | Data: | Mai-2020 | Local de edição ou do evento: | University of Science and Technology of China | Resumo: | After the development of Deepface and DeepID methods in 2014, deep learning methods for image recognition has dramatically improved the state-of-the-art performance on Deep Convolutional Neural Networks (DCNNs) and reshaped the research landscape of image processing and data analysis. In spite of rapid improvement in deep learning algorithms, it still has various challenges like adjustment of appropriate loss function and optimization strategy to handle large scale problems in many computer vision applications including Face Recognition (FR) and Handwritten Digit Recognition (HDR). This thesis focus on these challenges and their better solution. | Descrição: | Documentos apresentados no âmbito do reconhecimento de graus e diplomas estrangeiros | URI: | https://hdl.handle.net/10316/95693 | Direitos: | openAccess |
Aparece nas coleções: | UC - Reconhecimento de graus e diplomas estrangeiros |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Thesis-jamshaid.pdf | Tese | 8.72 MB | Adobe PDF | Ver/Abrir |
Google ScholarTM
Verificar
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.