{"id":1189,"date":"2021-03-17T21:03:46","date_gmt":"2021-03-17T20:03:46","guid":{"rendered":"http:\/\/iwann.uma.es\/2021\/?page_id=1189"},"modified":"2021-03-31T10:01:24","modified_gmt":"2021-03-31T08:01:24","slug":"abstracts2","status":"publish","type":"page","link":"http:\/\/iwann-old.uma.es\/2021\/?page_id=1189","title":{"rendered":"Abstract S2"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t
\n\t\t\t\t

S2: Convolutional neural networks: beyond traditional solutions<\/h2>\n

Irina Perfilieva<\/h2>\n

Jan Platos<\/h2>\n

Jan Hula<\/h2>\n
University of Ostrava, Czech Republic<\/span><\/div>\n

Abstract<\/h2>\nThere are many variants of CNN architecture in the literature, but the entire structure of CNN is mainly in two parts. The first part is used for feature extraction, and the second part processes the regression and consists of fully connected layers and an output layer.\n\nFeature extraction is related to network architecture and its ability to get a good data representation. In general, the good representation is a particular problem that is connected with a sufficient statistics of training data that is minimal and invariant to future variability of the test data. However, there is still no comprehensive theory to explain how deep networks create optimal representations.<\/span>\n\nThe second part of CNN is determined by the choice of the loss function. In cases of classification, the latter is usually empirical cross-entropy, so the process is prone to overfitting. This problem is usually solved with regularization, which can be explicit or implicit in stochastic gradient descent. The choice of the regularizer is also responsible for the ability of the networks to accommodate the aforementioned future variability.<\/span>\n\nWe solicit contributions that relate to both the development of representation theory and developments in optimization and hardware that contribute to the further progress of deep neural networks. The following list of topics is suggested, but not limited to:<\/span>\n