3 papers
cs.LG2022
PathFinder: Discovering Decision Pathways in Deep Neural Networks
Ozan İrsoy, Ethem Alpaydın
Explainability is becoming an increasingly important topic for deep neural networks. Though the operation in convolutional layers is easier to understand, processing becomes opaque…
cs.LG2018
Dropout Regularization in Hierarchical Mixture of Experts
Ozan İrsoy, Ethem Alpaydın
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 i…
cs.LG2018
Continuously Constructive Deep Neural Networks
Ozan İrsoy, Ethem Alpaydın
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…