E
Ethem Alpaydin
Researcher at Özyeğin University
Publications - 101
Citations - 9221
Ethem Alpaydin is an academic researcher from Özyeğin University. The author has contributed to research in topics: Artificial neural network & Tree (data structure). The author has an hindex of 30, co-authored 100 publications receiving 8812 citations. Previous affiliations of Ethem Alpaydin include Boğaziçi University.
Papers
More filters
Book ChapterDOI
Weight Quantization for Multi-layer Perceptrons Using Soft Weight Sharing
TL;DR: This approach considers the weights of a multi-layer perceptron (MLP) not as constant numbers but as random variables drawn from a Gaussian mixture distribution; which includes as its special cases k-means clustering and uniform quantization.
Journal ArticleDOI
Continuously Constructive Deep Neural Networks
Ozan Irsoy,Ethem Alpaydin +1 more
TL;DR: In this paper, the authors propose two approaches that automatically update the network structure while also learning its weights, where the depth, or additional complexity, is encapsulated continuously in the parameter space through control parameters that add additional complexity.
Proceedings ArticleDOI
BeamECOC: A local search for the optimization of the ECOC matrix
TL;DR: While ECOC is one of the best solutions for multi-class problems, one issue which makes it suboptimal is that the training of the base classifiers is done independently of the generation of the code matrix.
Multiple Kernel Machines Using Localized Kernels
TL;DR: P X m=1 m n X i=1 i y i h m (x); m (X i )i | {z } K m ( x;x i ) +b Unweighted sum m = 1 8m Weighted sum (1) p P m =1 m = 2 and m 0 8m
Book ChapterDOI
Bagging Soft Decision Trees
TL;DR: It is shown that the bagged soft trees generalize better than single soft trees and bagged hard trees and on 27 two-class classification data sets (ten of which are from the medical domain), and 26 regression data sets, it is shown how the parameters of the newly-added nodes are learned using gradient-descent.