Zobrazeno 1 - 10
of 310
pro vyhledávání: '"Alpaydın, Ethem"'
Autor:
İrsoy, Ozan, Alpaydın, Ethem
Explainability is becoming an increasingly important topic for deep neural networks. Though the operation in convolutional layers is easier to understand, processing becomes opaque in fully-connected layers. The basic idea in our work is that each in
Externí odkaz:
http://arxiv.org/abs/2210.00319
Autor:
Ahmetoğlu, Alper, Alpaydın, Ethem
Generative adversarial networks (GANs) are deep neural networks that allow us to sample from an arbitrary probability distribution without explicitly estimating the distribution. There is a generator that takes a latent vector as input and transforms
Externí odkaz:
http://arxiv.org/abs/1911.02069
Autor:
İrsoy, Ozan, Alpaydın, Ethem
Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision tree where
Externí odkaz:
http://arxiv.org/abs/1812.10158
Autor:
İrsoy, Ozan, Alpaydın, Ethem
Traditionally, deep learning algorithms update the network weights whereas the network architecture is chosen manually, using a process of trial and error. In this work, we propose two novel approaches that automatically update the network structure
Externí odkaz:
http://arxiv.org/abs/1804.02491
Autor:
İrsoy, Ozan, Alpaydın, Ethem
Recently proposed budding tree is a decision tree algorithm in which every node is part internal node and part leaf. This allows representing every decision tree in a continuous parameter space, and therefore a budding tree can be jointly trained wit
Externí odkaz:
http://arxiv.org/abs/1412.6388
Autor:
İrsoy, Ozan, Alpaydın, Ethem
We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall output is t
Externí odkaz:
http://arxiv.org/abs/1409.7461
Autor:
Yildiz, Olcay Taner, Alpaydin, Ethem
Statistical tests that compare classification algorithms are univariate and use a single performance measure, e.g., misclassification error, $F$ measure, AUC, and so on. In multivariate tests, comparison is done using multiple measures simultaneously
Externí odkaz:
http://arxiv.org/abs/1409.4566