Ioannis E. Livieris received his B.Sc., M.Sc. and Ph.D. degrees in Mathematics from the University of Patras, Greece in 2006, 2008 and 2012 respectively. His research interests include numerical optimization, neural networks and its application in bioinformatics. He is a member of the ESDLab since 2008. See his personal web page.
Degrees
 2012: Ph.D. from Department of Mathematics, University of Patras.
 2008: M.Sc. in "Computational Mathematics & Informatics", Department of Mathematics, University of Patras, Greece.
 2006: Bachelor Degree in Mathematics (speciality in Computational Mathematics & Informatics), Department of Mathematics, University of Patras, Greece.
Dissertations
 Ph.D. Thesis: Nonlinear Conjugate Gradient Methods for Optimization and Neural Network Training. Supervisor: Professor P. Pintelas.
 M.Sc. Thesis: Performance Evaluation of Algorithms for Neural Network Training and Applications. Supevisor: Professor P. Pintelas.
 B.Sc. Thesis: Constraint Propagation Problems. Bachelor Thesis Supevisor: Associate Professor T.N. Grapsa.
Courses
Email :
This email address is being protected from spambots. You need JavaScript enabled to view it
Phone : 2610 997833
Fax : 2610 997313

A decision support system for predicting students’ performance 



A limited memory descent Perry conjugate gradient method 



A new class of nonmonotone conjugate gradient training algorithms 



A modified Perry conjugate gradient method and its global convergence 



A new conjugate gradient algorithm for training neural networks based on a modified secant equation 



A new class of spectral conjugate gradient methods based on a modified secant equation for unconstrained optimization 



Globally convergent modified Perry conjugate gradient method 



An improved spectral conjugate gradient neural network training algorithm 



I.E. Livieris and P. Pintelas, An Improved Spectral Conjugate Gradient Neural Network Training Algorithm, International Journal on Artificial Intelligence and Tools, 20(1), 2012. 
Read more...

A descent DaiLiao conjugate gradient method based on a modified secant equation and its global convergence 



An advanced conjugate gradient training algorithm based on a modified secant equation 



Predicting students' performance using artificial neural networks 



A memoryless BFGS Neural network training algorithm 



M.S. Apostolopoulou, D.G. Sotiropoulos, I.E. Livieris and P. Pintelas, A Memoryless BFGS Neural Network Training Algorithm, In Proceedings of 6th IEEE International Conference on Industrial Informatics (INDIN 2009), p.p. 216221, 2009. 
Read more...

Performance evaluation of descent CG methods for neural network training 



I.E. Livieris and P. Pintelas, Performance Evaluation of Descent CG Methods for Neural Network Training, In Proceedings of The 9th Hellenic European Research on Computer Mathematics & Conference its Applications (HERCMA 2009), vol 11, pp. 4046, Athens, 2009. 
Read more...

Classification of large biomedical data using ANNs based on BFGS method 



I.E. Livieris, M.S. Apostolopoulou, D.G. Sotiropoulos, S.A. Sioutas and P. Pintelas, Classification of Large Biomedical Data using ANNs based on BFGS method. In Proceedings of 13th Panhellenic Conference on Informatics (PCI 2009), 2009 
Read more...

On descent spectral CG algorithms for training recurrent neural networks 



I.E. Livieris D.G. Sotiropoulos and P. Pintelas, On Descent Spectral CG Algorithms for Training Recurrent Neural Networks. In Proceedings of 13th Panhellenic Conference on Informatics (PCI 2009), 2009. 
Read more...

A greedy approach to transversal selection for nonlinear systems of equations 



D.G. Sotiropoulos and I.E. Livieris A Greedy Approach to Transversal Selection for Nonlinear Systems of Equations, In Proceedings of Conference in Numerical Analysis (NumAn07), pp 134136, Kalamata, September, 2007. 
Read more...


