prof. dr hab. inż. Bogdan Wilamowski
Dane kontaktowe
Katedra Elektroniki i Telekomunikacji

Kielnarowa 386a, pok. KM102 (CEM)
36-020 Tyczyn
tel. 17 866 11 05
Terminy konsultacji
Konsultacje do ustalenia przez e-mail:
wilam(AT)ieee.org

Nota biograficzna
Wybitny specjalista elektronik i informatyk, profesor i wykładowca na Wydziale Elektroniki i Inżynierii Komputerowej oraz Dyrektor Centrum Technologii Mikro i Nano Technologicznych Mikroelektronicznych w Stanie Alabama. Byl zalozycielem i Vice Prezydentem IEEE Computational Intelligence Society, a nastepnie Prezydentem IEEE Industrial Electronics Society. Był edytorem szeregu czasopism naukowych takich jak: International Journal of Circuit Systems and Computers, IES Newsletter, IEEE Transactions on Neural Networks, IEEE Transactions on Education, Journal of Computing, International Journal of Hybrid Intelligent Systems, Journal of Intelligent and Fuzzy Systems. Byl zalozycielem IEEE Trans. on Industrial Informatics, a obecnie jest Redaktorem Naczenym IEEE Transactions on Industrial Electronics, ktory jest jednym z najwiekszych periodykow IEEE z okolo 70 Associate Editors i baza okolo 2000 recenzentow z ponad 80 krajow.
Działalność naukowo-dydaktyczna
Badania:
  • Nowe podejścia do efektywnego uczenia złożonych systemów inteligentnych, projekt badawczy NCN (UMO-2015/17/B/ST6/01880): , termin realizacji: 04.2016-03.2018
  • Inteligentne nieliniowe systemy o płytkich i głębokich architekturach, projekt badawczy NCN (UMO-2013/11/B/ST6/01337): , termin realizacji: 07.2014-12.2016
Prowadzone zajęcia:
  • Seminarium dyplomowe
  • Seminarium magisterskie
  • Wykład monograficzny (Metody komputerowej inteligencji)
Materiały dla studentów
Materiały dydaktyczne dla studentów są udostępnione na dysku K:\BWilamowski sieci uczelnianej.
Publikacje
  • Z. Su; J. Kolbusz; B. M. Wilamowski, Linearization of Bipolar Amplifiers Based on Neural-Network Training Algorithm , IEEE Transactions on Industrial Electronics, 2016, Volume: 63, Issue: 6, pp3737 - 3744
  • Jordan Richardson; Janusz Korniak; Philip D. Reiner; Bogdan M. Wilamowski, Nearest-Neighbor Spline Approximation (NNSA) Improvement to TSK Fuzzy Systems, IEEE Transactions on Industrial Informatics, 2016, Volume: 12, Issue: 1, pp: 169 - 178
  • P. Rozycki, J. Kolbusz, B. M. Wilamowski, Estimation of Deep Neural Networks Capabilities Based on a Trigonometric Approach, INES 2016, Budapest
  • X. Wu, P. Rozycki, B. M. Wilamowski, Single Layer Feedforward Networks Construction Based on Orthogonal Least Square and Particle Swarm Optimization, ICAISC 2016, Zakopane, 158-169
  • P. Rozycki, J. Kolbusz, R. Korostenskyi, B. M. Wilamowski, Estimation of Deep Neural Networks Capabilities Using Polynomial Approach, ICAISC 2016, Zakopane, pp. 136-147
  • P. Różycki, J. Kolbusz, B. Wilamowski,  Dedicated Deep Neural Network Architectures and Methods for Their Training, IEEE 19th International Conference on Intelligent Engineering Systems (INES'15) Bratislava,  3-5 September 2015, pp. 73-78
  • P. Różycki, J. Kolbusz, T. Bartczak, B. Wilamowski, Using Parity-N Problems as a Way to Compare Abilities of Shallow, Very Shallow and Very Deep Architectures, Lecture Notes in Computer Science, vol. 9119, ICAISC 2015, Zakopane, pp. 112-122
  • M. Pukish, P. Różycki, B. Wilamowski, PolyNet - A Polynomial-Based Learning Machine for Universal Approximation, IEEE Transactions on Industrial Informatics, 2015, Volume: 11, Issue: 3, pp. 708 - 716 (IF=8.785)
  • C. Cecati, J. Kolbusz, P. Siano, P. Różycki, B. Wilamowski, A novel RBF Training Algorithm for Short-term Electric Load Forecasting: Comparative Studies, IEEE Transactions on Industrial Electronics, 2015, Volume: 62,  Issue: 10, pp. 6519 - 6529 (IF=6.498)
  • X. Wu, P. Różycki, B. Wilamowski, Hybride Constructive Algorithm for Single – Layer Feeforward Network Learning, IEEE Transactions on Neural Networks and Learning Systems, 2015, Volume:26, Issue: 8, pp. 1659-1668 (IF=4.291)
  • Yu, H.; Reiner, P.D.; Xie, T.; Bartczak, T.; Wilamowski, B.M., "An Incremental Design of Radial Basis Function Networks," Neural Networks and Learning Systems, IEEE Transactions on , vol.25, no.10, pp.1793-1803, Oct. 2014
  • D. Hunter, Hao Yu, M. S. Pukish, J. Kolbusz, and B.M. Wilamowski, “Selection of Proper Neural Network Sizes and Architectures—A Comparative Study”, IEEE Trans. on Industrial Informatics, vol. 8, May 2012, pp. 228-240.
  • T. Xie, H. Yu, J. Hewlett, P. Rozycki, B. Wilamowski " Fast and Efficient Second-Order Method for Training Radial Basis Function Networks ," IEEE Trans. on Neural Networks and Learning Systems, vol. 23, no. 4, pp. 609 - 619 , Apr 2012.
  • B. M. Wilamowski, Hao Yu, and Kun Tao Chung “Parity-N Problems as a Vehicle to Compare Efficiency of Neural Network Architectures” Industrial Electronics Handbook, vol. 5 – Intelligent Systems, 2nd Edition, chapter 10, pp. 10-1 to 10-8, CRC Press 2011.
  • B. M. Wilamowski, H. Yu, “Improved Computation for Levenberg Marquardt Training,” IEEE Trans. on Neural Networks, vol. 21, no. 6, pp. 930-937, June 2010.
  • B. M. Wilamowski and H. Yu, “Neural Network Learning Without Backpropagation," IEEE Trans. on Neural Networks, vol. 21, no.11, pp1793-1803, Nov. 2010.
  • B. M. Wilamowski, “Neural Network Architectures and Learning algorithms- How Not to Be Frustrated with Neural Networks”, IEEE Industrial Electronics Magazine, vol 3, no 4, pp.56-63, (2009) (best paper award).
  • B. M. Wilamowski, N. J. Cotton, O. Kaynak, and G. Dundar, "Computing Gradient Vector and Jacobian Matrix in Arbitrarily Connected Neural Networks," IEEE Trans. on Industrial Electronics, vol. 55, no. 10, pp. 3784-3790, Oct 2008.
  • B. M. Wilamowski, D. Hunter, and A. Malinowski, "Solving parity-N problems with feedforward neural networks," Proc. 2003 IEEE IJCNN, 2546-2551, IEEE Press, 2003.
  • B. M. Wilamowski and R. C. Jaeger, " Implementation of RBF Networks by Feedforward Sigmoidal Neural Networks," Intelligent Engineering Systems Through Artificial Neural Networks vol. 7, ed. C. H. Dagli and others, New York 1997, pp. 183-188
  • B. M. Wilamowski and L. Torvik, " Modification of Gradient Computation in the Back-Propagation Algorithm", presented at ANNIE'93 - Artificial Neural Networks in Engineering, St. Louis, Missouri, Nov.14-17, 1993, pp. 175-180,