- Katedra Zastosowań Systemów Informatycznych, CEM Kielnarowa pok.
KM202, tel. (17866) 1108, -prosić dr Leszka Gajeckiego (Sekrtetarza
Katedry, sekretarz też może byc dostępny pod tel. 1471 - pok.RA4),
- kontakt przez sekretarza Katedry/ contact through
Chair secreatary: Lgajecki (at) wsiz. rzeszow. pl (w miejscu (at)
wstawić @, instead of (at) put the @ )
Konsultacje - do umówienia w trakcie przyjazdów Profesora
A. Starzyk received M.S. degree in applied mathematics and Ph.D. degree
in electrical engineering both from Warsaw University of Technology,
Warsaw, Poland, and habilitation degree in electrical engineering from
Silesian University of Technology in Gliwice, Poland. He worked as an
Assistant Professor at the Institute of Electronics Fundamentals, Warsaw
University of Technology, Warsaw, Poland. Subsequently, he spent two
years as a Post-Doctorate Fellow and research engineer at McMaster
University, Hamilton, Canada. Since 1991 he has been a professor of
Electrical Engineering and Computer Science, at Ohio University, Athens,
Ohio, USA, and a director of Embodied Intelligence Lab. Since 2009 he
has been the head of Department of Applied Information Systems at WSIiZ,
cooperated with the National Institute of Standards and Technology in
the area of testing and mixed signal fault diagnosis for eight years. He
has been a consultant to Magnetek Corp. and a visiting professor at
University of Florence, Italy. He was a technical advisor and Senior
Scientist at Magnolia Broadband Inc.. For several summers he was a
visiting faculty at Wright Labs - Advanced Systems Research Group and at
Redstone Arsenal - U.S. Army Test, Measurement, and Diagnostic
Activity. For one year he held the position of an IPA fellow at Wright
Research Labs, Automatic Target Recognition Group. He was a visiting
researcher at ATT Bell Laboratories - VLSI Systems Research Group and
Sarnoff Research Labs. - Mixed Signal VLSI Design Group.
research includes embodied machine intelligence, self-organizing goal
driven learning, motivating mechanisms for sensory-motor interactions,
associative spatio-temporal memories, episodic memories as well as
applications of machine learning to intelligent control of robots and
virtual agents, building virtual environments, pattern analysis, data
mining, and financial markets.
Motivated Learning in Virtual Environments
for Robots and Avatars
research is focused on the design and development of computational
systems that learn, operate and communicate in a changing, unpredictable
environment by developing high-level sensory representation of the
environment and developing their own motor abilities. The objective is
to design biologically inspired, self-organizing, motivated learning
(ML) and problem-solving tools in order to build powerful systems
capable of formulating and achieving complex goals using limited
learning will develop cognitive agents, which will analyze and act upon
available information, seek further information and pursue predefined
goals according to their own, internally developed behavioral patterns.
The objective is to enhance understanding of the role of interaction
with environment for perception, cognition and interaction. This
development is based on the mechanism of motivated learning that uses
self-organization, goal creation and goal driven learning (including
hierarchical reinforcement and curiosity based learning). Research is
focused on theoretical aspects of motivated cognitive systems
development and their practical applications to robots and virtual
important question is how to motivate an agent to do anything, and in
particular, to enhance its own complexity? An answer to this question
may be provided by the motivated learning idea. ML yields EI agents
that set their own goals and develop internal reward systems. By
providing an agent with the internal drive to learn, set its own
objectives, and evaluate success of its actions, motivated learning may
lead to an intelligent behavior. A ML agent receives reinforcement from
environment for its most primitive objectives; however, it does not
suffer from quick growth of the learning effort in a complex
environment. It uses a goal creation system (GCS) to define and manage
abstract goals. ML improves agent’s ability to perceive useful objects
and learn useful motor skills.
The webpage of project Organization of Semantic and Episodic Memory in Motivated Learning of Robots": ncn.wsiz.rzeszow.pl
Inteligentne Systemy Autonomiczne - wyklad
courses in Digital Design, Analog and Digital VLSI, Computer Aided
Analysis, Digital Test and Testable Design, VHDL Hardware Description
Language with FPGA Design, Machine Intelligence.
Some new publications are at the webpage of project Organization of Semantic and Episodic Memory in Motivated Learning of Robots": ncn.wsiz.rzeszow.pl
Chapters in books
J. A. Starzyk, Motivated Learning for Computational Intelligence,
in Computational Modeling and Simulation of Intellect: Current State and Future Perspectives, edited by B. Igelnik,
IGI Publishing, ch.11, pp. 265-292, 2011.
A. Starzyk, Y. Liu, S. Batóg, “A Novel Optimization Algorithm Based on
Reinforcement Learning”, in `Computational Intelligence in
Optimization-Applications and Implementations', Tenne,
Yoel; Goh, Chi-Keong (Eds.), Springer Verlag, 2010, pp. 27-49.
"Introduction to Computer Design and Analysis of Electronic Networks", (Co‑author), Wydawnictwa PW, Warszawa, 1978 (in Polish).
of Polish translation "Computer‑aided analysis of electronic circuits,
algorithms and computational techniques", by L.O. Chua and P.M. Lin,
Wydawnictwa Naukowo‑Techniczne, Warszawa, 1981
"Advances in Circuits and Systems - Selected Papers on Analog Fault Diagnosis", (co-author), IEEE Press, New York 1987.
"Analog Methods for Circuit Analysis and Diagnosis", (Co‑author), Marcel Dekker, Inc., New York, 1988.
J. A. Starzyk, “Topological Analysis and Diagnosis of Analog Circuits”, Wydawnictwa Politechniki Slaskiej, 2008, 140 pp.
A. Starzyk, "Motivation in Embodied Intelligence" in Frontiers in
Robotics, Automation and Control, I-Tech Education and Publishing,
Austria, 2008, pp. 83-110
J. A. Starzyk, and Basawaraj, “Memristor Crossbar Architecture for
Synchronous Neural Networks”, IEEE Trans. Circuits and Systems, Part I,
March 2014, pp.1-12.
V. A. Nguyen, J. A. Starzyk and W-B. Goh,"A Spatio-temporal Long-term Memory Approach for Visual
Place Recognition in Mobile Robotic Navigation" –Robotics and
Autonomous Systems, Elsevier, vol.
61, no. 12, Dec. 2013, pp. 1744–1758.
W. Wang, B. Subagdja, A.-H. Tan, and J. A. Starzyk, “Neural Modeling of
Episodic Memory: Encoding, Retrieval, and Forgetting” IEEE Trans on
Neural Networks and Learning Systems, vol.
23, no. 10, Oct. 2012, pp. 1574 - 1586.
Huang, C. Li, S. Duan, and J. A. Starzyk, "Robust exponential stability
of uncertain delayed neural networks with stochastic perturbation and
IEEE Trans on Neural Networks and Learning Systems, vol. 23 , no. 6 , June 2012, pp.
866 – 875.<
V. A. Nguyen, J. A. Starzyk, W-B. Goh, D. Jachyra, “Neural Network Structure for
Spatio-Temporal Long-Term Memory” IEEE Trans on Neural Networks and
Learning Systems, vol. 23 no. 6, June, 2012, pp. 971-983.
J. A. Starzyk, J. T. Graham, P.
Raif, and A-H.Tan, “Motivated
Learning for Autonomous Robots Development”, Cognitive Science Research, v.14, no.1, 2012, p.10(16) pp. 10-25.
P. Moghadam, J. A. Starzyk, and W. S. Wijesoma, "Fast Vanishing Point
Detection in Unstructured Environments" IEEE Trans. on Image Processing, vol. 21, no. 1, Jan 2012,
J. A. Starzyk and D. Prasad, “A
Computational Model of Machine Consciousness” International Journal of Machine Consciousness, vol. 3, No. 2 (2011) pp. 255-281.
J. Feng, W-H. Qiu, J. Starzyk, “Risk Assessment of Credit Card Application
Based on Self-organizing Learning Array (SOLAR)”, Industrial
Engineering Journal, vol. 13, no. 6, pp. 71-75.
A. Starzyk, H. He, “Spatio-Temporal Memories for Machine Learning: A
Long-Term Memory Organization”, IEEE Trans. on Neural Networks, vol.
20, no. 5, May 2009, pp 768 - 780.
He, X. Shen, J. A. Starzyk, ”Power Quality Disturbances Analysis Based
on EDMRA Method”, accepted for Int. Journal of Electrical Power &
Energy Systems, vol. 31, no.5, May 2009.
Y. Liu, J. A. Starzyk, Z. Zhu, “Optimized Approximation Algorithm in Neural Network without Overfitting”, IEEE Trans. on Neural Networks, vol. 19, no. 4, June, 2008, pp. 983-995.
H. F. A. Hamed, S. Kaya, J. A. Starzyk, “Use of nano-scale double-gate MOSFETs in low-power tunable current mode analog circuits” Analog Integrated Circuits and Signal Processing, Feb., 2008.
J. A. Starzyk, and H. He, “Anticipation-Based Temporal Sequences Learning in Hierarchical Structure”,
IEEE Trans. on Neural Networks, vol. 18, no. 2, March 2007, pp. 344 –
358. Received the best research paper award in the College of
Engineering and Technology at Ohio University.
J. A. Starzyk and H. He, “A Novel Low Power Logic Circuit Design Scheme,” IEEE Trans. Circuits Syst. II, vol. 54, no. 2, pp.176-180, Feb. 2007.
Z. Zhu, F. van Graas and J. A. Starzyk, “GPS signal acquisition using the repeatability of successive code phase measurements” GPS Solutions, Springer, May 2007.
S. Kaya, H. F. A. Hamed and J. A. Starzyk, “Low-Power Tunable Analog Circuit Blocks Based on Nanoscale Double-Gate MOSFETs,” IEEE Trans. Circuits Syst. II, vol. 54, no. 7, July 2007, pp. 571-575.
J. A. Starzyk, H. He, and Y. Li, “A Hierarchical Self-organizing Associative Memory for Machine Learning”, Lecture Notes in Computer Science 4491: pp. 413-423, 2007.
J. A. Starzyk, Y. Liu, D. Vogel, ”Sparse Coding in Sparse Winner Networks”, Lecture Notes in Computer Science 4492: pp. 534-541, 2007.
Z. Zhu, H. He, J.A. Starzyk, and C. Tseng “Self-Organizing Learning Array and its Application to Economic and Financial Problems” Elsevier Science, Information Sciences, vol. 177, no 5, 1 March 2007, Pages 1180-1192.
J. A. Starzyk, M. Ding, Y. Liu, ”Hybrid Pipeline Structure for Self-Organizing Learning Array”, Lecture Notes in Computer Science, 2007.
H. He, and J. A. Starzyk, “Online Dynamic Value System for Machine Learning”, Lecture Notes in Computer Science 4491: pp. 441-448, 2007.
J. A. Starzyk, Z. Zhu, and Y. Li, "Associative Learning in Hierarchical Self Organizing Learning Arrays“, IEEE Trans. Neural Networks, vol.17, no. 6, pp.1460-1470, Nov. 2006.
H. He and J. A. Starzyk, "A Self Organizing Learning Array System for Power Quality Classification based on Wavelet Transform", IEEE Trans. on Power Delivery, Jan. 2006.
J. A. Starzyk, Z. Zhu and T.-H. Liu "Self-Organizing Learning Array" IEEE Trans. on Neural Networks, vol. 16, no. 2, pp. 355-363, March 2005.
J. A. Starzyk, Z. Zhu, and Y. Li, "Associative Learning in Hierarchical Self Organizing Learning Arrays", Artificial Neural Networks: Biological Inspirations. Lecture Notes in Computer Science 3696: pp. 91-96, 2005.
Janusz A. Starzyk, and Yue Li, David D. Vogel, "Neural Network with Memory and Cognitive Functions", Artificial Neural Networks: Biological Inspirations. Lecture Notes in Computer Science 3696: pp. 85-90, 2005.
J. A. Starzyk, Dong Liu, Zhi-Hong Liu, D. Nelson, and J. Rutkowski, “Entropy-based optimum test points selection for analog fault dictionary techniques,” IEEE Transactions on Instrumentation and Measurement, vol. 53, no. 3, June 2004, pp. 754-761.
J. A. Starzyk and F. Wang, "Dynamic Probability Estimator for Machine Learning" IEEE Trans. on Neural Networks, vol.15, no 2, March 2004, pp.298-308.
J. A. Starzyk, R. P. Mohn, and L. Jing, L., "A Cost-Effective Approach to the Design and Layout of a 14-b Current-Steering DAC Macrocell", IEEE Trans. on Circuits and Systems I: Fundamental Theory and Applications, Vol. 51 , no. 1, Jan. 2004, pp. 196 - 200.
D. E. Nelson, J. A. Starzyk, and D. D. Ensley, "Iterated wavelet transformation and signal discrimination for HRR radar target recognition", IEEE Trans. on Systems, Man and Cybernetics, Part A ,Vol. 33 , no.1 , Jan. 2003 , pp. 52 - 57.
D. Liu and J. A. Starzyk, " A generalized fault diagnosis in dynamic analog circuits" Int. Journal of Circuit Theory and Applications, vol. 30, 2002, pp. 487-510.
D. E. Nelson, J. A. Starzyk, and D. D. Ensley, "Iterative Wavelet Transformation and Signal Discrimination for HRR Radar Target Recognition," Multidimensional Systems and Signal Processing, Vol. 14, no.2. 2002.
J. Becker, A. Alsolaim, M. Glesner, and J. Starzyk, “A
Parallel Dynamically Reconfigurable Architecture for Flexible
Aplication-Tailored Hardware/Software Systems in Future Mobile
Communication”, The Journal of Supercomputing, Erratum Vol. 23, 132, 2002, 19(1): 105-127 (2001).
J. Pang and J. A. Starzyk, "Fault Diagnosis in Mixed-Signal Low Testability System" An Int. Journal of Analog Integrated Circuits and Signal Processing, vol. 28, no.2, August 2001, pp. 159-170.
J. A. Starzyk and Y.-W. Jan, and F. Qiu, "A DC-DC Charge Pump Based on Voltage Doublers", IEEE Trans. Circuits and Systems, Part I, vol. 48, no. 3, March 2001, pp. 350-359.
G. N. Stenbakken, D. Liu J. A. Starzyk, and B. C. Waltrip, "Nonrandom Quatization Errors in Timebases", IEEE Trans. on Instrumentation and Measurement, vol. 50, no. 4, Aug. 2001, pp.888-892.
J. A. Starzyk, D. E. Nelson, and K. Sturtz, " A Mathematical Foundation for Improved Reduct Generation in Information Systems", Journal of Knowledge and Information Systems, v. 2 n. 2, March 2000 p.131-146.
J. A. Starzyk, J. Pang, S. Manetti, G. Fedi, and C. Piccirilli, "Finding Ambiguity Groups in Low Testability Analog Circuits", IEEE Trans. Circuits and Systems, Part I, vol 47, no. 8, 2000, pp. 1125-1137.
G. Fedi, S. Manetti, J. A. Starzyk, M. C. Piccirilli "Determination of an Optimum Set of Testable Components in the Fault Diagnosis of Analog Circuits", IEEE Trans. Circuits and Systems, Part I, vol. 46, no.7, 1999, 779-787.
J. A. Starzyk, D. E. Nelson, and K. Sturtz, "Reduct Generation in Information Systems", Bulletin of International Rough Set Society, 1999, 3 (1/2).
J. A. Starzyk, "Hierarchical Analysis of High Frequency Interconnect Networks", IEEE Trans. on Computer Aided Design of Integrated Circuits and Systems, vol.13, no.5, 1994, pp. 658-664.
J. A. Starzyk and X. Fang, "A CMOS Current Mode Winner-Take-All Circuit with both Excitatory and Inhibitory Feedback", Electronics Letters, 1993.
G. N. Stenbakken and J. A. Starzyk, "Diakoptic and Large Change Sensitivity Analysis", IEE Proc. G, Circuits, Devices and Systems, vol. 139, no.1, 1992, pp.114-118.
J. A. Starzyk and H. Dai, "A Decomposition Approach for Testing Large Analog Networks," Journal of Electronic Testing - Theory and Applications, no.3, 1992, pp. 181-195.
J. A. Starzyk and A. Konczykowska, "Flowgraph Analysis of Large Electronic Networks", IEEE Trans. on Circuits and Systems, vol. CAS-33, 1986.
J. A. Starzyk and E. Sliwa, "Upward Topological Analysis of Large Circuits Using Directed Graph Representation", IEEE Trans. on Circuits and Systems, vol. CAS-31, 1984, pp. 410-414.
E. Salama, J. A. Starzyk and J. W. Bandler, "A Unified Decomposition Approach for Fault Location in Large Analog Circuits", IEEE Trans. on Circuits and Systems, vol. CAS-31, 1984, pp. 609-622.
J. A. Starzyk, R. M. Biernacki and J. W. Bandler, "Evaluation of Faulty Elements within Linear Subnetworks", Int. Journal of Circuit Theory and Applications, vol. 12, 1984, pp. 23-37.
J. A. Starzyk and J. W. Bandler, "Multiport Approach to Multiple-Fault Location in Analog Circuits", IEEE Trans. on Circuits and Systems, vol. CAS-30, 1983, pp. 762-765.
J. A. Starzyk, "An Efficient Cluster Algorithm", Acta Polytechnica, CVUT, Praha, 1981, pp. 49-55.
J. A. Starzyk, "Signal Flow-Graph Analysis by Decomposition Method", IEE Proc. on Electronic Circuits and Systems, No. 2, April 1980, pp. 81-86.
G. Centkowski and J. A. Starzyk, "Topological Synthesis of LLF Networks", Acta Polytechnica, CVUT, Praha, 1980, pp. 77-86.
J. A. Starzyk and E. Sliwa, "Hierarchic Decomposition Method for the Topological Analysis of Electronic Networks", Int. Journal of Circuit Theory and Applications, Vol. 8, 1980, pp. 407-417.
A. Starzyk, "Generation of Complete Trees by the Method of Modified
Structural Matrix", Arch. Elektrot., z.4, 1978, (in Polish), pp.
A. Starzyk, "New Method for Designing Complete Trees of a Pair of
Conjugate Graphs", Arch. Elektrot., z.1, 1977, (in Polish), pp. 41-46.
A. Starzyk, "Application of the Controlled Expansions Method to the
Topological Analysis of Circuits", Arch. Elektrot., z.1, 1977, (in
Polish), pp. 47-58.
A. Starzyk, "Determination of the Nullator-Norator Graph's Complete
Trees", Radio Electronics and Communication Systems, t.XX 12, 1977, (in
Russian), pp. 9-15.
A. Starzyk, and J. Wojciechowski, "Topological Analysis and Synthesis
of Electrical Networks by the Method of Structural Numbers", Raport
Naukowy IPE, Warszawa, 1977, (in Polish).
A. Starzyk, "Topological Synthesis of Linear Active Networks Described
by Multivariable Functions", Arch. Elektrot., z.2, 1976, (in Polish),
A. Starzyk, "Topological Methods of Analysis of LSL Networks with
Nullators and Norators", Prace Naukowe PW, Elektronika, No. 20,
Warszawa, 1975, (in Polish), pp. 73-89.
A. Starzyk, "Topological, Analysis of LSL Networks with Nullators and
Norators; Impedance Dependencies", Prace Naukowe PW, Elektronika, No.
20, Warszawa, 1975, (in Polish), pp. 61-71.
A. Starzyk, "Complement of Columns of Constant-row Structural Number to
the Factorizable Number", Arch. Elektrot., z.2, 1975 (in Polish), pp.
and J. A. Starzyk "Determination of Structural Number of a Partitioned
Graph. Part I and II.", Arch. Elektrot z.2, 1975, (in Polish), pp.