გიორგი ლეკიშვილი
ქემოინფორმატიკა, ქიმიური გრაფების თეორია, ხელოვნური ინტელექტი ქიმიაში.
სრული პროფილი ამჟამად ხელმისაწვდომია ინგლისურ ენაზე.
Education
1991 Rustavi 21st grammar school, cum laude 1995 Javakhishvili University, summa cum laude Programming languages Python/Jython, Java, C/C++, C#; lisp, ruby (less experienced) Methods Soft modeling (PCR/PLS, etc.), Neural networks (Kohonen SOM, Counter-Propagation NN, Back-Propagation NN, RBF NN, etc.) Optimization (GA, SimAn) Miscellaneous Linear algebra & graph theory algorithms, understanding of formal linguistics and compiler design
Publications
Lekishvili, G. On the Characterization of Molecular StereoStructure: 1. Cis-Trans Isomerism, J. Chem. Inf. Comput. Sci., 1997, 37, 924-928. Lekishvili, G. On the Characterization of Molecular StereoStructure: 2. The invariants of the Two-dimensional Graphs. MATCH - Commun. Math. Comput. Chem., 2001, 43, 136-152; Lekishvili, G. The Data. In: Chemoinformatics, A Textbook. Gasteiger, J, Engel, T., Eds. Wiley-VCH, Weinhem, 2003. Lekishvili, G. A New Molecular Descriptor Based on the Kernel of Atomic Properties: 1. General Concepts. Georg. Chem. J. 2004, 4, 333-334. Lekishvili, G. A New Molecular Descriptor Based on the Kernel of Atomic Properties: 2. Benchmark Steroid Dataset. 2006 (to be submitted - the abstract available from http://docs.lekishvili.info/kap2.doc)
Future work plans
?
