Browsing by Author "Karatsiolis, Savvas"

Now showing items 1-8 of 8

    • Article  

      Conditional Generative Denoising Autoencoder 

      Karatsiolis, Savvas; Schizas, Christos N. (2019)
      We present a generative denoising autoencoder model that has an embedded data classifier in its architecture in order to take advantage of class-based discriminating features and produce better data samples. The proposed ...
    • Doctoral Thesis  Open Access

      Conditional generative denoising autoencoder 

      Karatsiolis, Savvas (Πανεπιστήμιο Κύπρου, Σχολή Θετικών και Εφαρμοσμένων Επιστημών / University of Cyprus, Faculty of Pure and Applied Sciences, 2019-12)
      Η διατριβή μελετά ανοικτά προβλήματα στο χώρο της Μηχανικής Μάθησης και προτείνει μοντέλα επίλυσης ή μετριασμού τους. Ένα από αυτά τα προβλήματα είναι η σύνθεση εικόνων που υπόκειται σε συγκεκριμένες συνθήκες. Προτείνεται ...
    • Article  

      Feature mapping through maximization of the atomic interclass distances 

      Karatsiolis, Savvas; Schizas, Christos N. (2015)
      We discuss a way of implementing feature mapping for classification problems by expressing the given data through a set of functions comprising of a mixture of convex functions. In this way, a certain pattern’s potential ...
    • Conference Object  

      Implementing a software cache for genetic programming algorithms for reducing execution time 

      Karatsiolis, Savvas; Schizas, Christos N. (INSTICC Press, 2014)
      A cache holding reusable computations that are carried out during the execution of a genetic algorithm is implemented and maintained in order to improve the performance of the genetic algorithm itself. The main idea is ...
    • Conference Object  

      Modular Domain-to-Domain Translation Network 

      Karatsiolis, Savvas; Schizas, Christos N.; Petkov, Nicolai (Springer International Publishing, 2018)
      We present a method for constructing and training a deep domain-to-domain translation network: two datasets describing the same classes (i.e. the source and target domains) are used to train a deep network that can translate ...
    • Article  

      Modular domain-to-domain translation network 

      Karatsiolis, Savvas; Schizas, Christos N.; Petkov, Nicolai (2020)
      Domain-to-domain translation methods map images from a source domain to corresponding images from a target domain. The two domains contain images from the same classes, but these images look different. Recent approaches ...
    • Conference Object  

      Region based Support Vector Machine algorithm for medical diagnosis on Pima Indian Diabetes dataset 

      Karatsiolis, Savvas; Schizas, Christos N. (2012)
      The problem of diagnosing Pima Indian Diabetes from data obtained from the UCI Repository of Machine Learning Databases[6] is handled with a modified Support Vector Machine strategy. Performance comparison with previous ...
    • Conference Object  

      Variable target values neural network for dealing with extremely imbalanced datasets 

      Karatsiolis, Savvas; Schizas, Christos N. (Springer Verlag, 2016)
      An original classification algorithm is proposed for dealing with extremely imbalanced datasets that often appear in biomedical problems. Its originality comes from the way a neural network is trained in order to get a ...