Desenvolvendo Modelos de Deep Learning para Aplicações Multimídia no Tensorflow. Busson, A. J. G.; Figueiredo, L. C.; Santos, G. P. d.; Damasceno, A. L. d. B.; Colcher, S.; and Milidiú, R. L. In Anais do XXIII Simpósio Brasileiro de Sistemas Multimídia e Web: Minicursos, pages 67–116.
Desenvolvendo Modelos de Deep Learning para Aplicações Multimídia no Tensorflow [pdf]Paper  abstract   bibtex   
The availability of massive quantities of data, combined with increasing computational capabilities, makes it possible to develop more precise Machine Learning algorithms. These new tools provide advances in areas such as Natural Language Processing and Computer Vision, allowing efficient processing of images, text and audio. Now, cognitive functionalities, such as learning, recognition and detection, can be used in multimedia applications to create mechanisms beyond traditional capture, streaming and presentation uses. Methods based on Deep Learning became state-of-the-art in several Multimedia challenges. This short course presents the grounds and ways to develop models using Deep Learning. It prepares the participant to: (1) understand and develop models based on Deep Neural Networks, Convolutional Neural Networks (CNN), Recurrent Neural Networks, including LSTM and GRU; (2) apply the Deep Learning models to solve problems within the multimedia domain like Image Classification, Facial Recognition, Object Detection, Video Scenes Classification. The Python programming language is shown alongside TensorFlow, a package for developing Deep Learning models.
@incollection{busson_desenvolvendo_2018,
	title = {Desenvolvendo Modelos de Deep Learning para Aplicações Multimídia no Tensorflow},
	isbn = {978-85-7669-455-7},
	url = {https://webmedia.org.br/wp-content/uploads/2018/10/LivroDeMinicursosWebMedia2018.pdf},
	abstract = {The availability of massive quantities of data, combined with increasing computational capabilities, makes it possible to develop more precise Machine Learning algorithms. These new tools provide advances in areas such as Natural Language Processing and Computer Vision, allowing efficient processing of images, text and audio. Now, cognitive functionalities, such as learning, recognition and detection, can be used in multimedia applications to create mechanisms beyond traditional capture, streaming and presentation uses. Methods based on Deep Learning became state-of-the-art in several Multimedia challenges. This short course presents the grounds and ways to develop models using Deep Learning. It prepares the participant to: (1) understand and develop models based on Deep Neural Networks, Convolutional Neural Networks ({CNN}), Recurrent Neural Networks, including {LSTM} and {GRU}; (2) apply the Deep Learning models to solve problems within the multimedia domain like Image Classification, Facial Recognition, Object Detection, Video Scenes Classification. The Python programming language is shown alongside {TensorFlow}, a package for developing Deep Learning models.},
	pages = {67--116},
	booktitle = {Anais do {XXIII} Simpósio Brasileiro de Sistemas Multimídia e Web: Minicursos},
	author = {Busson, Antonio José G. and Figueiredo, Lucas C. and Santos, Gabriel P. dos and Damasceno, André Luiz de B. and Colcher, Sérgio and Milidiú, Ruy L.},
	date = {2018},
	langid = {portuguese}
}
Downloads: 0