PUBLICATIONS OF INTELLIGENT ROBOTICS FACULTY, RELATED TO MACHINE LEARNING, ROBOTICS AND COMPUTATIONAL INTELLIGENCE

2003

• FUZZY LOGIC IN MACHINE LEARNING:
  
  
  1. Paul Burkey and Marek Perkowski, ``Efficient Decomposition of Large Fuzzy Functions and Relations,'' Proceedings of International Conference on Fuzzy Information Processing. Theories and Applications, March 1 -- 4, Beijing, China, Tsinghua University Press and Springer, pp. 145-154.
     Part 1. PDF format
     Part 2. PDF format
     Part 3. PDF format
     Part 1. Word format
     Part 2. Word format
     Part 3. Word format
     
     
  
  
  
• PROBABILISTIC ROBOTICS:
  
  
  1. Marek Perkowski, ``Probabilistic Robotics,'' Booklet of International Robotics Forum, April 17, 2003, KAIST, Korea.
     Slides in PDF format
     
     
  
  
  
• HUMANOID ROBOT DESIGN:
  
  
  1. Michele Folgheraiter, Giuseppina Gini, Marek Perkowski, and Mikhail Pivtoraiko, ``Blackfingers: a Sophisticated Hand Prosthesis,'' Proceedings of ICORR 2003 (the 8th International Conference on Rehabilitation Robotics), April 22-25, 2003, KAIST, Korea, pp. 238 -- 241.
     PDF format
     
     
  2. Michele Folgheraiter, Giuseppina Gini, Marek Perkowski, and Mikhail Pivtoraiko, ``Adaptive Reflex Control for an Artificial Hand,'' Proceedings of 7th IFAC Symposium on Robot Control, SYROCO 2003, Holliday Inn, Wroclaw, Poland, 1-3 September, 2003.
     PDF format
     
     
  
  
  
• MACHINE LEARNING FOR HUMANOID ROBOTS:
  
  
  1. Marek Perkowski, Tsutomu Sasao, Atsumu Iseno, Uland Wong, Mikhail Pivtoraiko, Michele Folgheraiter, Martin Lukac, David Ng, Miranda Fix and Karl Kuchs, ``Use of Machine Learning based on Constructive Induction in Dialogs with Robotic Heads,'' Proceedings of ICORR 2003 (the 8th International Conference on Rehabilitation Robotics), April 22-25, 2003, KAIST, Korea. pp. 326 -- 329.
     PDF format
     
     
  2. Anas Al-Rabadi, Martin Zwick, Marek Perkowski, ``A Comparison of Modified Reconstructability Analysis and Ashenhurst-Curtis Decomposition of Boolean Functions, Kybernetes, 2003.
     BAD. PDF format
     
     
     
  
  
  
• CAM BRAIN MACHINE DESIGN:
  
  
  1. Andrzej Buller, and Marek Perkowski, ``Cellular Automata Realization of Regular Logic,'' Booklet of 12th International Workshop on Post-Binary ULSI Systems, May 16, 2003, Meiji University, Japan, pp. 53 -- 60.
     PDF format
     
     
  2. Andrzej Buller, and Marek Perkowski, ``Evolved Reversible Cascades Realized on the CAM-Brain Machine (CBM),'' Proceedings of 2003 NASA/DoD Conference on Evolvable Hardware, July 9-11, 2003, Chicago, Illinois, USA. pp. 246 -- 251.
     Word format
     
     

2002

• SPECIALIZED FPGA CONTROLLERS FOR SOFT COMPUTING:
  
  
  1. Marek Perkowski, Lech Jozwiak, David Foote, Qihong Chen, Anas Al-Rabadi, ``Learning in Hardware using Multiple-Valued Logic,''
     Part 1 of the article in PDF format.
     Part 2 of the article in PDF format.
     
     
  
  
  
• DATA MINING AND MACHINE LEARNING:
  
  
  1. Stanislaw Grygiel, Martin Zwick and Marek Perkowski, ``Multi-Level Decomposition of Probabilistic Relations,'' Book of Abstracts of the 12th International WOSC Congress and the 4th International Institute for General System Studies (IIGS) workshop, Pittsburgh, Pennsylvania, p. xx, 24-26 March 2002.
     PDF format
     
     
  2. Anas Al-Rabadi, Martin Zwick and Marek Perkowski, ``A Comparison of Enhanced Reconstructability Analysis and Ashenhurst-Curtis Decomposition of Boolean Functions,'' Book of Abstracts of the 12th International WOSC Congress and the 4th International Institute for General System Studies (IIGS) workshop, Pittsburgh, Pennsylvania, p. 12, 24-26 March 2002.
     Abstract in HTML format
     
     
  
  
  
• APPLICATIONS OF MACHINE LEARNING IN HUMANOID ROBOTICS:
  
  
  1. Uland Wong, and Marek Perkowski, ``A New Approach to Robot's Imitation of Behaviors by Decomposition of Multiple-Valued Relations,'' Proceedings of Symposium on Boolean Problems. September, 2002, Freiberg, Germany.
     PDF format
     
     
  
  
  
• SIGNAL PROCESSING:
  
  
  1. J. McNames, "Fourier Series Analysis of Epicyclic Gearbox Vibration," Transactions of the ASME, Journal of Vibration and Acoustics, in press (January 2002, Vol. 124).
     
     
  2. J. McNames, "Local Averaging Optimization for Chaotic Time Series Prediction," Neurocomputing, in press.
     
     
  3. J. McNames, "A Nearest Trajectory Strategy for Time Series Prediction," Proceedings of the International Workshop on Advanced Black-Box Techniques for Nonlinear Modeling, Katholieke Universiteit Leuven, Belgium, pp. 112-128, July 1998.

2001

• EVOLUTIONARY METHODS:
  
  
  1. G. Greenwood and Q. Zhu, ''Convergence in Evolutionary Programs with Self-Adaptation'', Evolutionary Computation, Vol. 9, No. 2, pp. 147-158, 2001.
     
     
  2. G. Greenwood, ''Finding Solutions to NP Problems: Philosophical Differences Between Quantum and Evolutionary Search Algorithms'', Congress on Evolutionary Computation 2001.
  
  
  
• DECISION DIAGRAMS AND DATA STRUCTURES:
  
  
  1. Y. Jiang, Y. Wang, X. Song, Y. Savaria, `` Computation of Signal Output Probability for Boolean Function Represented by OBDD,'' VLSI Design: An International Journal of Custom-Chip Design, Simulation, and Testing, 2001.
     
     
  2. W. Hung, X. Song, ``BDD Minimization by Scatter Search,'' IEEE Transactions on Computer-Aided Design, 2001.
     
     
  3. J. Zhou, X. Ye, X. Song, ``On Reachability Graphs for Petri Nets,'' International Journal of Computers & Electrical Engineering, Elsevier Science Publishers, 2001.
  
  
  
• EMBEDDED SYSTEMS:
  
  
  1. X. Song, etc. ``Formal verification of embedded systems using multiway decision graphs,'' International Journal of Multiple-Valued Logic, The Gordon and Breach Publishing, 2001.
  
  
  
• COGNITIVE ROBOTS:
  
  
  1. Buller, A., Shimohara, K., ``Kansei in a Psychodynamic Agent,'' Proceedings, International Symposium: Toward a Development of KANSEI Technology (KANSEI 2001), October 5-6, 2001, Muroran, Hokkaido, Japan, 177-180.
     
     
  2. Buller, A., Kaiser, L, Shimohara, K. ``Para-evolutionary Paradigm of Reasoning,'' In: Baba N, Jain LC, Howlett RJ (Eds.) Knowledge-Based Intelligent Information Engineering Systems & Allied Technologies (KES'2001), Part 1, Amsterdam: IOS Press, 127-131.
     
     
  3. Buller, A., ``Dynamic Fuzzy Sets for Cognitive Modeling,'' The Sixth International Symposium on Artificial Life and Robotics (AROB 6th '01), January 15-17, 2001, Tokyo, Japan, 150-151.
     
     
  4. Buller, A., Chodakowski, T., Kaiser, L., Nowak, A., Shimohara, K., ``MemeStorms: Cellular Working Memory and Dynamics of Judgments,'' The Sixth International Symposium on Artificial Life and Robotics (AROB 6th '01), January 15-17, 2001, Tokyo, Japan, 146-149.
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. J. McNames, "A Fast Nearest Neighbor Algorithm Based on a Principal Axis Tree," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 9, pp. 964-976, September 2001.
     
     
  2. Stanislaw Grygiel and Marek Perkowski, ``Labeled rough partitions - a new general purpose representation for multiple-valued functions and relations'', Journal of Systems Architecture, Vol. 47, 2001, pp. 29-59.
     
     
     
     
  3. Anas Al-Rabadi, Martin Zwick and Marek Perkowski, ``Reconstructability Analysis versus Ashenhurst/Curtis decomposition,'' Proc. General Systems, August 2001.
     
     
  4. Anas Al-Rabadi, Martin Zwick and Marek Perkowski, ``Reconstructability Analysis versus Ashenhurst/Curtis decomposition,'' Proc. LDL, August 2001.
     
     
  5. Alan Mishchenko, Bernd Steinbach, and Marek Perkowski, ``Bi-Decomposition of Multi-Valued Relations,'' Proc. 10-th Inernational Workshop on Logic and Synthesis, IWLS'01 , pp. 35 - 40, Granlibakken, CA, June 12 - 15, 2001, IEEE Computer Society and ACM SIGDA. Slides in PDF
     
     
     
     
  6. Marek Perkowski, and Stanislaw Grygiel, `` Decomposition of Relations: A New Approach to Constructive Induction in Machine Learning and Data Mining - An Overview'' Proc. Workshop organized by the National Institute of Telecommunications and Polish Association for Logic and Philosophy of Science, May 25, 2001, pp. 91 - 111, Warsaw, Poland. Slides in PDF

2000

• COGNITIVE ROBOTS:
  
  
  1. Buller, A., Nowak, A., and Shimohara, K., ``Social Judgment and the Buterfly Effect,'' International Journal of Psychology, 35 (3/4), 303. (Presented orally at the XXVII Intenational Congress of Psychology, 23-28 July 2000, Stockholm, Sweden).
     
     
  2. de Garis, H., Buller, A., Dob, T., Honlet, J., Guttikonda, P. and D. Decesare, ``Building Multimodule Systems withy Unlimited Evolvable Capacities from Modules with Limited Evolvable Capacities (MECs),'' Proceedings of The Second NASA / DoD Workshop on Evolvable Hardware, July 13-15, Palo Alto, California, 225-234.
     
     
  3. Buller, A. and K. Shimohara, ``Does the 'Butterfly Effect' Take Place in Human Working Memory?,'' The Fifth International Symposium on Artificial Life and Robotics (AROB 5th '00), January 26-28, 2000, Oita, Japan, 204-207.
     
     
  4. Buller, A., Shimohara, K., Chodakowski, T., and H. Hemmi, ``CoDi Technique: Cellular Automata as Neural Networks,'' The Fifth International Symposium on Artificial Life and Robotics (AROB 5th '00), January 26-28, 2000, Oita, Japan, 192-195.
  
  
  
• BIOMETRIC TECHNOLOGIES:
  
  
  1. Vladimir Shmerko, Phil Philips, W. Rogers, Marek Perkowski and Svetlana Yanushkevich, ``Biometric Technologies'', Techniki Komputerowe, Information Bulletin of Institute of Mathematical Machines, Vol. XXXV, No. 1, 2000. pp. 1 - 30. (in English with Polish abstract).
     
     
  
  
  
• ROBOTICS:
  
  
  1. Marek Perkowski, ``Oregon Cyber Theatre,'' Proc. 3rd LDL.
  
  
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Marek Perkowski, ``Multiple-Valued Logic. Invitation to Collaboration,'' Proc. 3rd LDL.
     
     
  2. Karen Dill and Marek Perkowski, ``Multi-Strategic Cybernetic Problem-Solver,'' Proc. 3rd LDL.
     
     
     
     
  3. Alan Mishchenko, Craig Files, Marek Perkowski, Bernd Steinbach, and Christina Dorotska, ``Implicit Algorithms for Multi-Valued Input Support Manipulation,'' Proc. of 4th Intl. Workshop on Boolean Problems, September 2000, Freiberg, Germany, pp. 9 - 20.
  
  
  
• EVOLUTIONARY METHODS:
  
  
  1. S. Ahire, G. Greenwood, A. Gupta and M. Terwilliger, ''Workforce-Constrained Preventive Maintenance Scheduling Using Evolution Strategies'', Decision Sciences Journal, Vol. 31, No. 4, pp. 833-859, 2000.
     
     
  2. X. Hu, G. Greenwood and S. Ravichandran, ''Modeling Epistatic Interactions in Fitness Landscapes'', Congress on Evolutionary Computation 2000, pp. 932-938, 2000.
     
     
  3. G. Fogel, G. Greenwood and K. Chellapilla, ''Evolutionary Computation with Exinction: Experiments and Analysis'', Congress on Evolutionary Computation 2000, pp. 1415-1420, 2000.
     
     
  4. D. Miller, G. Greenwood and C. Ide, ''On the Use of Biologically-Inspired Adaptive Mutations to Evolve Artificial Neural Network Structures'', Proceedings of the 2000 IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (ECNN2000), pp. 24-32, 2000.
  
  
  
• SIGNAL PROCESSING:
  
  
  1. J. McNames, "Rotated Partial Distance Search for Faster Vector Quantization Encoding," IEEE Signal Processing Letters, Vol. 7, No. 9, pp. 244-246, September 2000.
     
     
  2. E. M. Huff, E. Barszcz, I. Y. Tumer, M. Dzwonczyk, J. McNames, "Experimental Analysis of Steady-State Maneuvering Effects on Transmission Vibration Patterns Recorded in an AH-1 Cobra Helicopter," In The Vertical Flight Society's 56th Annual Forum, American Helicopter Society, Virginia Beach, VA, pp. 642-653, May 2000 (Best Paper Award).
     
     
  3. J. McNames, "Local Modeling Optimization for Time Series Prediction," In Proceedings of the 8th European Symposium on Artificial Neural Networks, Bruges, Belgium, pp. 305-310, April 2000.
  
  
  
• PROBABILISTIC METHODS:
  
  
  
  1. X. Song, J. Zhou, X. Ye, ``A probabilistic prediction for traffic flow analysis,'' International Journal of Applied Mathematics, Academic Publishers, volume 2(12), 2000.
  
  
  

1999

• SEARCH AND PLANNING:
  
  
  1. Bart Massey, ``Directions In Planning: Understanding The Flow Of Time In Planning,'' Ph.D. Dissertation, University of Oregon, 1999.
     Describes techniques for reversing the direction of a planning problem and for measuring the directional bias of a planner, and uses these techniques to gain some insight into planning directionality issues. Also available in University of Oregon Technical Report format.
  2. Bart Massey, ``Worldwide Aeronautical Route Planner (Intelligent Systems Demonstration),'' with Charles B. McVey, David P. Clements, and Andrew J. Parkes. Proceedings of the 1999 National Conference on Artificial Intelligence, Orlando, Florida 1999.
     Describes an automated system for rapidly calculating aircraft routes in three-dimensional space. The routes are provably optimal under reasonable assumptions, and up to 5% better than routes calculated by a current commercial system.
  
  
  
• COGNITIVE ROBOTS:
  
  
  1. Buller, A., and K. Shimohara, ``Decision Making as a Debate in the Society of Memes in a Neural Working Memory,'' The Journal of 3D Images, 13 (3), pp. 77-82, 1999.
     
     
  2. de Garis, H., Nawa, N.E., Buller, A., Korkin, M., Gers, F., and M. Hough, ``Evolution of Neural Network Modules: ATR's Artificial Brain Project,'' In: L.C. Jain (Ed.), Evolution of Engineering and Information Systems and Their Applications, CRC Press: Boca Raton, London, New York, Washington, D.C., pp. 231-274, 1999.
     
     
  3. de Garis, H., Buller, A., Korkin, M., Gers, F., Nawa, N.E. and M. Hough, ``ATR's Artificial Brain ("CAM-Brain") Project : A Sample of What Individual "CoDi-1Bit" Model Evolved Neural Net Modules Can Do with Digital and Analog I/O,'' Proceedings of The First NASA / DoD Workshop on Evolvable Hardware, July 19-21, Pasadena, California, 102-110, 1999.
     
     
  4. Buller, A., ``Fuzziness, mega-networks and CoDi technique,'', Proc. 4th Conference on Neural Networks and Their Applications, May 18-22, Zakopane, Poland, 1999.
  
  
  
• EVOLUTIONARY METHODS:
  
  
  1. Gary Greenwood, ``Revisiting the Complexity of Finding Globally Minimum Energy Configurations in Atomic Clusters'', Zeitschrift für Physikalische Chemie Vol. 211, 105-114, 1999
     
     
     
  2. X. Hu, G. Greenwood, S. Ravichandran, and G. Quan, ``A Framework for User Assisted Design Space Exploration'', Proc. ACM/IEEE Design Automation Conference, pp. 414-419, 1999
  
  
  
• NEURAL NETWORKS:
  
  
  1. Lendaris, G., T. Shannon & A. Rustan, " A Comparison of Training Algorithms for DHP Adaptive Critic Neuro- control", submitted to IJCNN’99, Washington, DC, July, 1999. HTML Abstract
     
     
  2. Rustan, A., "Improving Hardware Branch Predictors Using Neural Networks", submitted to IJCNN’99, Washington, DC, July, 1999.
     
     
  3. Lendaris, G., T. Shannon & M. Zwick, "Prestructuring Neural Networks for Pattern Recognition Using Extended Dependency Analysis", invited paper to be presented at Applications and Science of Computational Intelligence II – AeroSense’99, Orlando, FL, SPIE, April, 1999.
     
     
  4. Lendaris, G.G., K. Mathia & R. Saeks, "Linear Hopfield Networks and Constrained Optimization", Transactions of Systems, Man & Cybernetics, IEEE, vol , xxx, 1999.
     
     
  5. Lendaris, G. & T. Shannon, "Designing (Approximate) Optimal Controllers via DHP Adaptive Critics & Neural Networks", invited chapter in The Handbook of Applied Computational Intelligence, Karayiannis, Padgett & Zadeh, eds., CRC Press, to appear.

  
  
  
• SIGNAL PROCESSING:
  
  
  1. McNames, J., "A Fast Nearest Neighbor Algorithm Based on a Principal Axis Tree", submitted to Pattern Recognition, Oct. 1999.
     )
     
     
     
  2. McNames, J., Barszcz, E., Dzwonczyk, M., and E. Huff, "Fourier Series Analysis of Synchronous Averages in Epicyclic Gearboxes", under review by coauthors, Aug. 1999.
     
     
     
  3. McNames, J., "Innovations in Local Modeling for Time Series Prediction", Ph.D. Thesis, Stanford University, May 1999.
     
     
     
     
  4. McNames, J., Suykens, J., and J. Vandewalle, "Winning Contribution of the K.U. Leuven time-series prediction competition", International Journal of Bifurcation and Chaos, Vol 9, No. 8, 1485-1500, Aug.1999.
     (Online Journal,
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M., Grygiel, S., Chen, Q., and D. Mattson, ``Constructive Induction Machines for Data Mining,'' Proc. Conference on Intelligent Electronics, Sendai, Japan, 14-19 March, 1999. Invited speaker.
     The concept of Learning Hardware introduced for the first time, restricted to combinational multiple-valued logic.
     
     
  2. Perkowski, M., Malvi, R., Grygiel,S., Burns, M., and A. Mishchenko, ``Graph Coloring Algorithms for Fast Evaluation of Curtis Decompositions,'' Proc. DAC'99, June 21-23 1999. (DAC 99). New Orleans, LA, USA, June 21-25, 1999.
     We show experimentally good results of our new graph coloring algorithm applied to functional decomposition.
     
     
  3. Perkowski, M.A., Chebotarev, A.N., and A. A. Mishchenko. Evolvable Hardware or Learning Hardware? Induction of State Machines from Temporal Logic Constraints. The First NASA/DOD Workshop on Evolvable Hardware (NASA/DOD-EH 99). Jet Propulsion Laboratory, Pasadena, California, USA,  July 19-21, 1999.
     A new concept of Learning Hardware has been introduced as a generalization of the concept of Evolvable Hardware. Instead of using only Genetic Algorithm in hardware, our model uses many approaches known from logic synthesis, especially synthesis of FSMs from L language declarative expressions. L Language was created by Chebotarev in Kiev.
     
     
  4. Steinbach, B., Perkowski, M., and Ch. Lang, ``Bi-Decomposition in Multi-Valued Logic for Data Mining,'' Proc. ISMVL'99, May, 1999.
     The well-known bi-decomposition algorithm for strongly unspecified Boolean functions of Bochmann and Steinbach was generalized to Multi-valued Logic.
     
     
  5. B. Steinbach, Ch. Lang, and M. Perkowski, ``EXOR-Decomposition of Sets of Functions,'' Proc. 4th International Workshop on Applications of the Reed-Müller Expansion in Circuit Design (Reed-Müller 99), University of Victoria, Victoria B.C., Canada, August 20-21, 1999.
     The concept of EXOR-decomposition has been extended to sets of functions. The concept of sets of relations has been introduced as a powerful generalization of relations.
     
     
  6. Lewis, T., Perkowski, M., and L. Jozwiak, ``Learning in Hardware: Architecture and Implementation of an FPGA-Based Rough Set Machine,'' Proceedings of the Euro-Micro'99 Conference, Milano, Italy, September 1999.
     Machine of Muraszkiewicz and Rybinski was generalized and realized in hardware (VHDL) for Rough Set theory applications.

1998

• COGNITIVE ROBOTS:
  
  
  1. Buller, A., and H. de Garis, ``Brain-Buliding Strategy: Some Remarks and Questions,'' Intelligent Information Systems (IIS'98), June 15-19, Malbork, Poland, 188-193, 1998.
  
  
  
• NEURAL NETWORKS:
  
  
  1. Lendaris, G. & T. Shannon, "Application Considerations for the DHP Methodology", Proceedings of the International Joint Conference on Neural Networks’98 (IJCNN’98), Anchorage, IEEE Press, May 1998. HTML Abstract
  
  
  
• EVOLUTIONARY METHODS:
  
  
  1. G. Greenwood and X. Hu, ``On the Use of Random Walks to Estimate Correlation in Fitness Landscapes'', Computational Statistics and Data Analysis Vol. 28, No. 2, pp. 131-137, 1998
     
     
  2. G. Greenwood, ``Efficient Construction of Self-Avoiding Walks for Protein Folding Simulations on a Torus'', Journal of Chemical Physics, Vol. 108, No. 18, pp. 7534-7537, 1998.
     
     
  3. G. Greenwood and Y. Liu, ``Finding Low Energy Conformations of Atomic Clusters Using Evolution Strategies,'' Proceedings of Evolutionary Programming VII, pp. 493-502, 1998.
     
     
  4. G. Greenwood and X. Hu, ``Are Landscapes for Constrained Optimization Problems Statistically Isotropic?'', Physica Scripta, Vol. 57, pp. 321-323, 1998.
     
     
  5. Dill, K., and M. Perkowski, ``Evolutionary Minimization of Generalized Reed-Muller Forms,'' Proc. ICCIMA'98 Conference, pp. 727-733, February 1998, Australia, published by World Scientific.
     Genetic Algorithm applied to GRMs. Full version of the paper.
  
  
  
• SIGNAL PROCESSING:
  
  
  1. McNames, J., "A nearest trajectory strategy for time series prediction", Proceedings of the International Workshop on Advanced Black-Box Techniques for Nonlinear Modeling, July 8-10, 1998, K.U. Leuven Belgium, pp.112-128.
     )
     
     
  2. Iravani, K., and M. Perkowski, ``Image Compression based on Reed-Muller Transforms,'' Proc. ICCIMA'98 Conference, pp. 81-95, February 1998, Australia, published by World Scientific.
     Postscript of Slides
     This paper showed that Reed-Muller Transform can be used for Image Compression, but in contrast to what some authors claimed in past, the results are not that great.
  
  
  
• BIOMETRIC TECHNOLOGIES:
  
  
  1. Shmerko, V. Dueck, G., Perkowski, M., Rodgers, W., Ross, D., and S. Yanushkevich, ``Bio-Technologies in Computing: The Promises and the Reality''. Proc. ICCIMA'98 Conference, pp. 396-409, February 1998, Australia, published by World Scientific.
     Figures for Presentation and the Biometric Technologies WWW Page.
     A tutorial paper about biometrics.
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M., Jozwiak, L., and S. Mohamed, ``New Approach to Learning Noisy Boolean Functions,'' Proc. ICCIMA'98 Conference, February 1998, Australia, published by World Scientific, pp. 693 - 706.
     The CDEC minimization problem from Logic Synthesis, generalized to functions with noise for Data Mining applications.
     
     
  2. Jozwiak, L., Perkowski, M., and D. Foote, ``Massively Parallel Structures of Specialized Reconfigurable Cellular Processors for Fast Symbolic Computations,'' Proc. MPCS'98 - The Third International Conference on Massively Parallel Computing Systems, Colorado Springs, Colorado - USA, April 6-9, 1998.
     Some additional ideas about Cube Calculus Machine, perhaps a better explanation than previous papers on CCM.
     
     
  3. Files, C., and M. Perkowski, ``Multi-Valued Functional Decomposition as a Machine Learning Method,'' Proc. ISMVL'98, May 1998.
     A tutorial paper that discusses peculiarities of using our decomposition techniques for Data Mining, as opposite to logic synthesis.
     
     
  4. Files, C., and M. Perkowski, ``An Error Reducing Approach to Machine Learning Using Multi-Valued Functional Decomposition,'' Proc. ISMVL'98, May 1998.
     Discussion of Functional Decomposition of Multiple-Valued functions for functions with errors. Application in Data Mining.
     
     
  5. Burns, M., Perkowski, M., and L. Jozwiak, ``An Efficient Approach to Decomposition of Multi-Output Boolean Functions with Large Sets of Bound Variables,'' Proc. 1998 Euromicro, pp. 16-23, Vasteras, Sweden, August 25-27, 1998.
     It was shown that for the functional decomposition with large sets of bound variables the efficiency can be much improved when a new algorithm to create graphs for coloring is used.
     
     
  6. Burns, M., Perkowski, M., Jozwiak, L., and S. Grygiel, ``An Efficient and Effective Approach to Column-Based Input/Output Encoding in Functional Decomposition,'' Proceedings of 3rd International Workshop on Boolean Problems, pp. 19-29, Freiberg University of Mining and Technology, Institute of Computer Science, September 17-18, 1998.
     An efficient algorithm is given.
     
     
  7. Malvi, R., Perkowski, M., and L. Jozwiak, ``Exact Graph Coloring for Functional Decomposition: Do we Need it?,'' pp. 1-10, Proceedings of 3rd International Workshop on Boolean Problems, Freiberg University of Mining and Technology, Institute of Computer Science, September 17-18, 1998.
     It is shown based on experiments, that exact graph coloring is not necessary to find good decompositions.
     
     
  8. Perkowski, M., Jozwiak, L., and C. Files, ``Minimization of Continuous-Input Sum of And-Or-Implicant Expressions for Data Mining Applications,'' Proceedings of 3rd International Workshop on Boolean Problems, pp. 125-131, Freiberg Academy of Mining and Technology, Institute of Computer Science, September 17-18, 1998.
     Generalization of the Hong's Data Mining Approach, in which instead of Sum of Continuous Intervals, the function uses L-, O- and C-shaped multi-valued continuous intervals.
     
     
  9. Grygiel, S., and M. Perkowski, ``New Compact Representation of Multiple-Valued Functions, Relations, and Non-deterministic State Machines,'' Proc. ICCD 1998, October 1998.
     Postscript of slides.
     A new representation that combines Binary Decision Diagrams and Cube Calculus.

1997

• EVOLUTIONARY METHODS:
  
  
  1. G. Greenwood, ``Characterization of Attractors in Speech Signals'', BioSystems, 44(2), 161-165, 1997

  2. G. Greenwood, ``Chaotic Behavior in Evolution Strategies'', Physica D, 109 (3-4), 343-350, 1997

  3. G. Greenwood, ``Training Partially Recurrent Neural Networks Using Evolutionary Strategies'', IEEE Transactions on Speech & Audio Processing, Vol 5, No 2, 192-194, 1997
     
     
     
  4. G. Greenwood, X. Hu and J. D'Ambrosio, ``Fitness Functions for Multipleobjective Optimization Problems: Combining Preferences with Pareto Rankings'' Foundations of Genetic Algorithms, R. Belew and M. Vose (Eds.), Morgan-Kaufmann, San Francisco, CA, 437-455, 1997
     
     
     
  5. Dill, K., Herzog, J., and M. Perkowski, ``Genetic Programming and its Application to the Synthesis of Digital Logic,'' Proc. PACRIM '97, Canada, August 20-22, 1997.
     One of early papers with ideas of using Genetic Programming to Logic Synthesis. Application to Data Mining.
     
     
     
  6. Dill, K., and M. Perkowski, ``Minimization of Generalized Reed-Muller Forms with Genetic Operators,'' Proc. Genetic Programming '97 Conf., July 1997, Stanford Univ., CA.
     One of early papers to use genetic algorithm for Reed-Muller logic.
  
  
  
• NEURAL NETWORKS:
  
  
  1. G. Greenwood, ``Training Multiple Layer Perceptrons to Recognize Attractors'', IEEE Transactions on Evolutionary Computation, Vol. 1, No. 4, 244-248, 1997
     
     
     
  2. Lendaris, G., "Prestructuring ANNs via A Priori Knowledge", Proceedings of SPIE International Conference, SPIE Press, April 1995.
     
     
     
  3. Lendaris, G., A. Rest & T. Misley, "Improving ANN Generalization Using A Priori Knowledge to Pre-Structure ANNs", Proceedings of International Conference on Neural Networks’97 (ICNN’97), IEEE Press, July 1997.
     
     
  4. Lendaris, G. and C. Paintz, "Training Strategies for Critic and Action Neural Networks in Dual Heuristic Programming Method", Proceedings of International Conference on Neural Networks’97 (ICNN’97), Houston, IEEE Press, pp712-717, June 1997.
     
     
  5. Lendaris, G., C. Paintz, & T. Shannon, "More on Training Strategies for Critic and Action neural Networks in Dual Heuristic Programming Method" (Invited Paper), Proceedings of Systems Man & Cybernetics Society International Conference’97, Orlando, IEEE Press, October, 1997. HTML Abstract -
     
     
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M.A., Jozwiak, L., and D. Foote, "Architecture of a Programmable FPGA Coprocessor for Constructive Induction Approach to Machine Learning and other Discrete Optimization Problems", in Reiner W. Hartenstein and Victor K. Prasanna (ed) ``Reconfigurable Architectures. High Performance by Configware,'' IT Press Verlag, Bruchsal, Germany, 1997, pp. 33 - 40.
     Reconfigurable processor for Cube Calculus machine, design and evaluation. Applications in very fast solving of combinatorial problems.
     
     
  2. Files, C., Drechsler, R., and M. Perkowski, "Functional Decomposition of MVL Functions using Multi-Valued Decision Diagrams," Proc. ISMVL'97, Halifax, Nova Scotia, Canada, May 1997, pp. 27 - 32.
     Slides of presentation of Craig Files at ISMVL'97:
     Postscript of the paper.
     Generalization of Pedram's decomposer to multiple-valued functions.
     
     
     
  3. Perkowski, M., Marek-Sadowska, M., Jozwiak, L., Luba, T., Grygiel, S., Nowicka, M., Malvi, R., Wang, Z., and J.S. Zhang, "Decomposition of Multiple-Valued Relations," Proc. ISMVL'97, Halifax, Nova Scotia, Canada, May 1997, pp. 13 - 18.
     postscript.
     The main paper of our group and collaborators, that explains our approach to decompose multiple-valued relations using special type of graph coloring. Good numerical results for benchmarks data taken from Machine Learning repositories.
     
     
  4. Grygiel, S., Perkowski, M., Marek-Sadowska, M., Luba, T., and L. Jozwiak, "Cube Diagram Bundles, A New Representation of Strongly Unspecified Multiple-Valued Functions and Relations," Proc. ISMVL'97, Halifax, Nova Scotia, Canada, May 1997, pp. 287 - 292.
     postscript
     We proposed a new representation of multiple-valued functions and relations that combines Binary Decision Diagrams and Cube Calculus. It is especially efficient for decomposition and solving multiple-valued equations, such as generalized satisfiability.
     
     
  5. Perkowski, M., and L. Jozwiak, ``FPGA-Based Hardware Architecture for Machine Learning based on Functional Decomposition,'' Invited paper, Proc. Conference on Logic Synthesis and Architecture, IFIP, Grenoble, France, December 1997.
     A hardware approach to simple processor for binary Ashenhurst-Curtis algorithm.
     
     

1996

• INFORMATION THEORY
  
  
  1. Fraser, A.M., "Chaos and Detection," Physical Review E, Vol. 53, No, 5, May 1996, pp. 4514-4523.
     
     
  
  
  
• EVOLUTIONARY METHODS:
  
  
  1. A. Gupta and G. Greenwood, ``Applications of Evolutionary Strategies to Fine Grained Task Scheduling'', Parallel Processing Letters, Vol 6, No 4, pp. 551-561, 1996
     
     
  2. E. DeDoncker, A. Gupta and G. Greenwood, ``Adaptive Integration Using Evolutionary Strategies,'' 3rd Int'l Conf. on High Performance Computing, pp. 94-99, 1996
     
     
     
  3. A. Gupta and G. Greenwood, ``Static Task Allocation Using (µ,lambda) Evolutionary Strategies'',Information Sciences, Vol 94, No 1-4, pp. 141-150, 1996.
  
  
  
• NEURAL NETWORKS:
  
  
  1. Lendaris, G. & K. Mathia, "Efficient Numerical Inversion Using Multilayer Feedforward Neural Networks", Proceedings of World Congress on Neural Networks’96 (WCNN-96), Earlbaum/INNS, August, 1996.
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M., Burns, M., Almeria, R., and N. Iliev, ``Approaches to the Input-Output Encoding Problem in Boolean Decomposition,'' PSU Electrical Engineering Department Report, January 9, 1996.
     postscript.
     
     One of reports with detailed analysis of various input-output encoding methods for decomposition.
     
     
  2. Sapiecha, P., Perkowski, M.A., and T. Luba, "Decomposition of Information Systems Based on Graph Coloring Heuristics," Symposium on Modelling, Analysis and Simulation, CESA'96 IMACS Multiconference, Lille, France, July 9-12, 1996.
     One more variant of decomposition based on graph coloring.

1995

• EVOLUTIONARY METHODS:
  
  
  1. G. Greenwood, ``On the Equity of Mutual Exclusion Algorithms in Distributed Systems'', Information Processing Letters, 56, pp. 19-22, 1995.
  
  
  
• NEURAL NETWORKS:
  
  
  1. Staib, W.E., and J. N. McNames, "Neural Networks Applied to Steelmaking", The Handbook of Brain Theory and Neural Networks, MIT Press, 1995.
     
     
  2. Baud-Bovy, Gabriel & G.G. Lendaris, "A Gaze-Addressing Control Interface Using Artificial Neural Networks",Proceedings of World Congress on Neural Networks’93(WCNN-93), Earlbaum/INNS, vol IV, pp. 527- 532, July, 1995.
     
     
  3. Mathia, K., G.G. Lendaris & R. Saeks, "Solving Nonlinear Equations using Recurrent Neural Networks", Proceedings of World Congress on Neural Networks’95(WCNN-95), Earlbaum/INNS, July, 1995.
     
     
  4. Willett, K. &. G. Lendaris, "Projection in Conceptual Graphs Using Neural Networks", Proceedings of NORTHCON-95, IEEE, Oct 1995.
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M.A., Ross, T., Gadd, D., Goldman, J.A., and N. Song, "Application of ESOP Minimization in Machine Learning and Knowledge Discovery," Proc. of the Second Workshop on Applications of Reed-Muller Expansion in Circuit Design, Chiba City, Japan, 27-29 August 1995, pp. 102-109.
     call html
     call postscript
     Sum-of-Product Minimization is a standard method used in Machine Learning. We propsed to use Exclusive-Sum-of-Products instead. The results were good only for functions with small percentage of don't cares.
     
     
  2. Perkowski, M.A., Luba, T., Grygiel, S., Burkey, P., Burns, M., Iliev, N., Kolsteren, M., Lisanke, R., Malvi, R., Wang, Z., Wu, H., Yang, F., Zhou, S., and J.S. Zhang, ``Unified Approach to Functional Decompositions of Switching Functions,'' PSU Electrical Engineering Department Report, December 29, 1995. postscript.
     A comprehensive study of new algorithms for decomposition, with applications in FPGA synthesis, layout mapping and Machine Learning.
     
     
  3. Perkowski, M., Burns, M., Luba, T., Grygiel, S., Stanley, C., Price, R., Wang, Z., Lu, J., Burkey, P., Manoharan, D., and S. Mohamed. ``Development of Search Strategies for MULTIS''. PSU Electrical Engineering Department Report, December 29, 1995. postscript.
     Various search strategies to be used in a multi-strategical functional decomposer for binary and multiple-valued functions and relations - especially for encoding and variable partitioning. Applications in Data Mining.

1994

• NEURAL NETWORKS:
  
  
  1. Lendaris, G., R. Pap, R. Saeks & C. Thomas, "Hardware Neural Network Implementation of Tracking System" Proceedings of 1994 IEEE Workshop on Neural Networks for Signal Processing (Greece), August 1994.
     
     
  2. Lendaris, G. & K Mathia, "Using A Priori Knowledge to Prestructure ANNs", Australian Journal of Intelligent Information Systems, vol 1, no 1, March 1994.
     
     
  3. Lendaris, G. & K. Mathia, "On Prestructuring ANNs Using A Priori Knowledge", Proceedings of World Congress on Neural Networks’94 (WCNN-94, San Diego), Earlbaum/INNS, June 1994.
     
     

1993

• TIME SERIES:
  
  
  1. Fraser, A.M., and A. Dimitriadis, "Forecasting Probability Densities by Using Hidden Markov Models with Mixed States," in Time Series Prediction: Forecasting the Future and Understanding the Past, edited by A. Weigend and N. Gershenfeld, Addison Wesley, 1993.
  
  
  
• NEURAL NETWORKS:
  
  
  1. Lendaris, G., M. Zwick & K. Mathia, "On Matching ANN Structure to Problem Domain Structure", Proceedings of World Congress on Neural Networks’93 (WCNN-93, Portland), Earlbaum/INNS, July 1993.
     
     
  2. Lendaris, G.G. & A.M. Fraser, "Visual Fitting and Extrapolation", in Time Series Prediciton: Forecastsing the Future and Understanding the Past, Weigend & Gershenfeld, eds, SFI Studies in the Sciences of Complexity, Proc. Vol XV, Addison-Wesley, 1993 [Second place winner in the Time Series Competition.]
     
     
  3. Perry, S.F. & G.G. Lendaris, "Competition Among Neural Agents in Economic Systems", Proceedings of World Congress on Neural Networks’93 (WCNN-93), Earlbaum/INNS, vol I, pp 198-202, July, 1993.

1992

• NEURAL NETWORKS:
  
  
  1. Lendaris, G. & D. Todd, "Use of Structured Problem Domain to Explore Development of Modularized Neural Networks", Proceedings of International Joint Conference on Neural Networks -’92 (IJCNN-92, Baltimore), IEEE, June 1992.
     
     
  2. Lendaris, G., "A Neural-Network Approach to Implementing Conceptual Graphs", (invited) Chapter 8 in Conceptual Structures, Nagle, et al, Editors, Ellis Horwood, 1992.
  
  
  
• ROBOT VISION:
  
  
  1. Espinosa, C., and M.A. Perkowski, "Hierarchical Hough Transform Based on Pyramidal Architecture," Proc. of the IPCCC'92, IEEE International Phoenix Conference on Computers and Communications, pp. 0743 - 0750, Scottsdale, Arizona, April 1-4, 1992.
     Application to robot images of PSUBOT from building interior.
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M.A., "A Universal Logic Machine," invited address, Proc. of the 22nd IEEE International Symposium on Multiple Valued Logic, ISMVL'92, pp. 262 - 271, Sendai, Japan, May 27-29, 1992.
     The concept of a Universal Logic Machine to solve combinatorial problems of design automation, machine learning and similar in hardware.

1991

• COMPUTER VISION AND PATTERN RECOGNITION:
  
  
  1. Perkowski, M.A., Wang, S., Spiller, W.K., Legate, A., and E. Pierzchala, "A Simple and Portable PC-based Image Processing System and its Application in Ovulometry," Proc. Imaging West 1990 Conference. pp. 758 - 763, Pasadena, CA, February 1990.
     A complete description of a software system for cervical mucus ferning patterns recognition.
     
     
  2. Perkowski, M., Sarabi, A., and I. Schaefer, "Application of Orthogonal Transforms in Image Processing," Proc. of Northcon '91, pp. 303 - 309, Portland, 1-3 October 1991.
     It was presented that Fixed-Polarity Reed-Muller transform that requires only exor operation and thus can be very fast, can be used instead of Walsh transform for some applications.
     
     
  3. Espinosa, C., and M.A. Perkowski, "Hierarchical Hough Transform Based on Pyramidal Architecture," Proc. of Northcon '91, pp. 291 - 296, Portland, 1-3 October 1991.
     A concept of hierachical Hough Transform that gives very good results for matching data retrieved from building interiors, such as doors and windows.
  
  
  
• ASSISTIVE ROBOTICS:
  
  
  1. Perkowski, M.A., and K. Stanton, "Robotics for the Handicapped," Proc. of Northcon '91, pp. 278 - 284, Portland, 1-3 October 1991.
     A general review of robotics for handicapped. Some original research characterized.

1990

• NEURAL NETWORKS
  
  
  1. Lendaris, G. & I. Harb, "Improved Generalization in ANNs via Use of Conceptual Graphs: A Character Recognition Task as an Example Case," Proceedings of International Joint Conference on Neural Networks’90 (IJCNN- 90, San Diego), IEEE, Jul 1990.
     
     
  2. Lendaris, G. & D.N. Todd, "Reachability Matrices Assist in Defining Neural Network Experiments," Proceedings of International Society for the Systems Sciences Conference-1990, ISSS, Jul 1990.
     
     
  3. Lendaris, G. "Conceptual Graphs as Vehicle for Improved Generalization in a Neural Network Pattern Recognition Task," Proceedings of AAAI Annual Workshop on Conceptual Graphs(AAAI-90), AAAI, Menlo Park, CA 94015, Aug. 1990.
     
     
  4. Lendaris, G. , "A Proposal for Indicating Quality of Generalization when Evaluating ANNs", Proceedings of the International Joint Conference on Neural Networks-1990 (IJCNN’90), San Diego, IEEE Press, July 1990.
  
  
  
• COMPUTER VISION AND PATTERN RECOGNITION:
  
  
  1. Perkowski, M.A., Wang, S., Spiller, W.K., Legate, A., and E. Pierzchala, "Ovulo-Computer: Application of Image Processing and Recognition to Mucus Ferning Patterns," Proc. of the Third IEEE Symposium on Computer-Based Medical Systems, pp. 52 - 59, Chapel Hill, North Carolina, June 3-6, 1990.
     The variant of the ovulocomputer that used image processing of cervical mucus ferning patterns under microscope. Method was based on convolution-based filtering and next Hough Transform and a perceptron and simple decision tree.
     
     
  
  
  
• MACHINE LEARNING AND DATA MINING:
  
  
  1. Perkowski, M.A., Dysko, P., and B. J. Falkowski, "Two Learning Methods for a Tree-Search Combinatorial Optimizer," Proc. of IEEE International Phoenix Conference on Computers and Communication, pp. 606 - 613, Scottsdale, Arizona, March 1990.
     This was an early paper that introduced the idea to combine search with perceptron-based heuristic evaluation function. It was used for minimizing boolean functions and similar problems. Also, the first paper to introduce general decision trees and diagrams, idea that led to the discovery of KFDDs.
     
     
  
  
  
• ASSISTIVE ROBOTICS:
  
  
  1. Stanton, K.B., Sherman, P.R., Rohwedder, M.L., Fleskes, Ch.P., Gray, D., Minh, D.T., Espinosa, C., Mayi, D., Ishaque, M., and M. A. Perkowski, "PSUBOT - A Voice-Controlled Wheelchair for the Handicapped," Proc. of the 33rd Midwest Symp. on Circuits and Systems, pp. 669 - 672, Alberta, Canada, August 1990.
     One of the first working robots for disabled. It had sonar, image processing based on Hough Transform, obstacle avoidance and pattern matching for build-in maps of PCAT building of PSU. Was able to navigate with accuracy of about 1.5 meter.
     
     

1989

1. Fraser, A.M., "Reconstructing Attractors from Scalar Time Series: A Comparison of Singular System and Redundancy Criteria," Physica D, Vol. D34, 1989, pp. 391-404.
   
   
2. Fraser, A.M., "Information and Entropy in Strange Attractors," IEEE Transactions on Information Theory, Vol. 35, No. 2, March 1989, pp. 245-262.
   
   
3. Lendaris, G., "Experiment on Implementing the Concept-Type Lattice in a Neural Network," Proceedings of AAAI Fourth Annual Workshop (AAAI-89/IJCAI-89) on Conceptual Graphs, AAAI, Menlo Park, CA 94025, July 1989.
   
   
4. Lendaris, G., "Testing the Use of a Neural Network to Implement a Basic Data-base Function," Proceedings of NORTHCON-89, IEEE, Oct 1989.
   
   

   1988

5. Lendaris, G., "Conceptual Graph Knowledge Systems as Problem Context for Neural Networks," Proceedings of the International Conference on Neural Networks ‘88 (ICNN-88, San Diego), IEEE, July 1988.
   
   
6. Lendaris, G., "Representing Conceptual Graphs for Parallel Processing," Proceedings of AAAI Third Annual Workshop On Conceptual Graphs (AAAI-88), AAAI, Menlo Park, CA 94015, Aug. 1988.
   
   
7. Lendaris, G., "Neural Networks, Potential Assistants To Knowledge Engineers," HEURISTICS, Journal of the International Association of Knowledge Engineers, Kensington, MD 20895, vol 1, no 2, Dec 1988.

   [Also, presented as Invited Paper at Third International Symposium on Knowledge Engineering, Oct 17-29, 1988, Madrid, Spain.]
   
   

   1986

8. Lendaris, G., "On Systemness and the Problem Solver: Tutorial Comments," IEEE Transactions on Systems, Man, and Cybernetics, v. SMC-16, no. 4, pp.604-610, Jul/Aug 1986.
   
   

   1985

   
   
   
9. Perkowski, M., "Systolic Architecture for the Logic Design Machine," Proc. of the IEEE and ACM International Conference on Computer Aided Design - ICCAD 85, pp. 133 - 135, Santa Clara, 19-21 November 1985.
   This was one of first papers to propose a satisfiability machine in hardware. The pipelined ring multi-processor solved also graph coloring and other problems.
   
   
10. Perkowski, M., and P.A. Frick, "Systolic Architecture for Multiplication of Polynomials and its Applications in Robotics," Proc. of Northcon '85, pp. 14/1.1 - 14/1.9, Portland, 1985.
    Description of a chip that multiplied in hardware two-dimensional polynomials (convolution) for robotics applications.
    
    
11. Perkowski, M., "A Systolic Processor for Approximate Solutions to NP-Complete Combinatorial Problems," Symposium on Complexity of Approximately Solved Problems. Computer Science Department, Columbia University, New York, April 17 -19 , 1985.
    A systolic processor of a regular structure that solved satisfiability, tautology, Petric function, Boolean equations, graph coloring and similar problems in hardware.
    
    

    1982

    
    
    
12. Perkowski, M., "General Methods for Solving Combinational Problems," In A. Goralski, (ed.), "Problem, method, solution," Vol. 4, Scientific-Technical Publishers, Warszawa, Poland, (in Polish), pp. 110-149, 1982.
    A book chapter about models to solve combinational problems using a computer.
    
    
13. Perkowski, M., "Digital Devices Design by Problem-Solving Transformations," Journal on Computers and Artificial Intelligence, Vol. 1, No. 4, pp. 343 - 365, August 1982.
    Rule-based program with backtracking, implemented in LISP, for optimizing multi-level logic networks with various gates and data path. An idea of ``high-level logic synthesis'' which optimizes structures of data path on the level of blocks such as registers and multiplexers, early idea of retiming transformations.
    
    

    1981

14. Krasinski, A., and M. Perkowski, "ORTOCARTAN - a New Computer Program for Analytic Calculations in General Relativity,"
    General Relativity and Gravitation, Vol. 13, No. 1, pp. 67 - 77, 1981.
    A Symbol manipulation program in LISP for applications in General Relativity. Symbolic differentation, substitutions, matrix and tensor operations and expressions simplification.
    
    
15. Krasinski, A., and M. Perkowski, "ORTOCARTAN - A New Computer Program for Algebraic Calculations," Computer Physics Communications, 22, pp. 269 - 271, 1981.
    This paper showed various applications of ORTOCARTAN in physics.
    
    
16. Perkowski, M., "Design Automation of Digital Systems as a New Domain for AI Research," Proc. of the VIth Symposium on Heuristic Methods, Polish Cybernetical Society, PTC, 1981.
    This paper showed that standard AI Search and rule-based methods can be practically used in many areas of digital design automation.
    
    
17. Perkowski, M., Kruszynski, H., Fijalkowski, W., and K. Kulpa, "A Multi-Parameter Microprocessor-Based Ovulation and Fertility Predictor/Indicator," Institute of Automatic Control, Technical University of Warsaw, 22 pages, 1981.
    This report introduced for the first time the image processing, ion analysis and pattern recognition methods for ovulation prediction and fertile phase monitoring.
    
    

    1980

18. Lendaris, G., "Structural Modeling, A Tutorial Guide," IEEE Transactions on Sys, Man, and Cybernetics, vSMC-10, no12, pp807-840, Dec 1980.
    
    
19. Dobrzynska, E., and M. Perkowski, "Description of the Problem Instead of the Description of the Solution Process: Heuristic Programming Languages," In A. Goralski, (ed.), "Problem, method, solution," Collection 3, Scientific - Technical Publishers, (in Polish), pp. 167-199, 1980.
    This book chapter presented logic programming languages such as Prolog and their applications.
    
    
20. Perkowski, M., "Digital Design by Problem-Solving Transformations," Proc. of the International Conference on "Artificial Intelligence and Information-Control Systems of Robots," pp. 18/1-18/19, Smolenice near Bratislava, Czechoslovakia, 30 June - 4 July, 1980.
    It was shown how rule-based programming can be used in a backtracking program for logic synthesis that could possibly search the entire search using small memory.
    
    
21. Perkowski, M., "Multistrategical Problem Solver," Proc. of the 2nd International Meeting on Intelligent Robotics and Knowledge Representation, Plenum Press, Repino near Leningrad, USSR, 12-19 October 1980.
    A new problem-description language for our MULTICOMP system was proposed here.
    
    

    1979

    
    
    
22. Lendaris, G., "On the Human Aspects in Structural Modeling," Technological Forecasting and Social Change, v 14, pp. 329-351, 1979.
    
    
    

    1978

    
    
    
23. Lendaris, G., M. Zwick & D. Schwartz, "Fuzziness and Catastrophe," Proceedings of the International Conference on Cybernetics and Society, IEEE, November 1978.
    
    
24. Magierska, S., and M. Perkowski, "On Analogy and its Formal Models," In A. Goralski, (ed.), "Problem, method, solution," Collection 2, Scientific - Technical Publishers, (in Polish), pp. 75-124, 1978.
    
    Discussion on analogical reasoning from the methodology and computer programming points of view.
    
    
25. Perkowski, M., "The State-Space Approach to the Design of Multipurpose Problem-Solver for Logic Design," "Artificial Intelligence and Pattern Recognition in Computer-Aided Design," In J. C. Latombe, (ed.), North Holland, Amsterdam, pp. 123-140, 1978.
    Applications of MULTICOMP to logic design problems such as set covering, state machine minimization and other combinational synthesis and FSM synthesis problems.
    
    
26. Krasinski, A., and M. Perkowski, "Symbolic Algebraic Computer Programs. Part II - applications and perspectives," Progress in Astronomy, Vol. XXVI, No. 1, pp. 33 - 49, (in Polish), 1978.
    Discussion of Lisp language from the point of view of applications to symbol manipulation in physics and astronomy.
    
    

    1977

    
    
    
27. Perkowski, M., "Heuristic Methods in Computer Science," In A. Goralski, (ed.), "Problem method solution," Collection 1, Scientific-Technical Publishers (WNT), (in Polish), 1977.
    This book chapter characterized heuristic search algorithms, especially to solve puzzles and combinatorial problems.
    
    
28. Perkowski, M., "An Application of General Problem-Solving Methods in Computer-Aided Design: the MULTICOMP System and its Problem-Oriented Source Language". Proc. of the IVth International Symposium on Heuristic Methods, PTC, Vol. 3., pp. 55 - 102, Warsaw, 24 September, 1977.
    This paper presented a general-purpose problem solver based on enhanced A* and backtracking strategies, as well as special declarative problem description language similar to ALICE.
    
    
29. Perkowski, M., "Some Concepts on Reasoning by Analogy. The Heuristic Programming Approach," Proc. of the IVth International Symposium on Heuristic Methods, Polish Cybernetical Society, PTC, Vol. 2, pp. 25 - 119, Warsaw, 24 September, 1977.
    This paper presented a model of reasoning based on analogy, it used the concept of relational structures and their similarities and other relations and operations on them.
    
    

    1976

30. Perkowski, M., "A Multipurpose and Multistrategic Program for Solving Combinatorial Problems," Proc. of the 3rd Symposium on Heuristic Methods, Vol. 3. pp. 23 - 90 (in Polish), Polish Cybernetical Society, Warsaw, 25 September 1976.
    This is a detailed description of General-Problem-Solver like program for solving combinatorial problems. It was much more efficient than original GPS for a wide class of problems.
    
    
31. Perkowski, M., Furmanik, A., Korwin-Mikke, J., Strzelec, M., Zielinski, K., Zniszczynski, J., and A. Goralski, "Variations on the Quadrangle (On Automatic Construction and Generalization of Problems - the Examples from Solid Geometry)," Proc. of the 3rd Symposium on Heuristic Methods, Vol. 1, pp. 181 - 198, (in Polish), Polish Cybernetical Society, Warsaw, 25 September 1976.
    This paper described a method to generate interesting problems in solid geometry using predicate calculus.
    
    

    1975

32. Lendaris, G. & S.B. Chism, Land-Use Classification of SKYLAB S-190B Photography Using Optical Fourier Transform Data, NASA, LBJ Space Center, Houston, Texas, Report No LEC-5633, March 1975.
    
    
33. Perkowski, M., Baczynski, W., and K. Jankowski, "Experiments with the Heuristic Program to Optimize Programs," Proc. of the IInd National Symposium on Heuristic Methods, Polish Cybernetical Society, PTC, Warsaw, Poland, (in Polish), 27 Sept. 1975.
    Discussion of applications of a program that optimizes flowcharts using rules, analogy, and similarity.
    
    
34. Perkowski, M., "An Approach to the Automatic Synthesis of Heuristic Problem-Solving Programs," Proc. of the IInd National Symposium on Heuristic Methods, pp. 28 - 43, (in Polish), Polish Cybernetical Society, PTC, Warsaw, Poland, 27 Sept. 1975.
    How to create search programs for particular tasks.
    
    
35. Perkowski, M., "Multiple Adaptive Identification Experiment with An Automaton," Institute of Automatic Control, Technical University of Warsaw, 1975, 4 pages.
    An efficient program to identify a finite state machine of well-known memory capacity and reset from input-output sequences.
    
    

    1974

36. Perkowski, M., "An Application of Heuristic Search Strategy in the Multiple, Adaptive Identification Experiment with Finite State Machines," Proc. of the First National Symposium on Heuristic Methods, pp. 135 - 152, (in Polish), Polish Cybernetical Society, PTC, Warsaw, 28 Sept. 1974.
    This method creates a minimal (Occam Razor) finite state machine based on observed input-output sequences. One of applications is in robot learning.
    
    

    1973

    
    
    
37. Lendaris, G., "Optical Preprocessing for Automatic Pattern Recognition," PROCEEDINGS, First International Congress on Pattern Recognition, Washington, DC, November 1973. (invited paper)
    
    

    1970

    
    
    
38. Lendaris, G. and G.L. Stanley, "Diffraction Pattern Sampling for Pattern Recognition," Proceedings of IEEE, v 58, No 2, pp. 198-216, February 1970. [A major paper].
    
    

    1965

    
    
    
39. Lendaris, G. and G.L. Stanley, "Self-Organization: Meaning and Means," Information Systems Sciences; Proceedings of the Second Congress, Baltimore: Spartan Books, 1965.
    
    
40. Lendaris, G. and G.L. Stanley, "Structure and Constraint in Discrete Adaptive Networks," Proceedings of the National Electronics Conference, v 21, October, 1965.
    
    

    1964

    
    
    
41. Lendaris, G., "On the Definition of Self-Organizing Systems," Proceedings of IEEE, vol. 52, March 1964.
    
    

    1963

    
    
    
42. Lendaris, G. & G.L. Stanley, On the Structure-Dependent Properties of Adaptive Logic Networks, GM Defense Research laboratories, TR63-219, July 1963.
    
    

    1962

    
    
    
43. Lendaris, G., "On the Identification of Linear Systems," TRANSACTIONS AIEE, Applications and Industry, September 1962.
    
    

    1961

44. Lendaris, G., On the Identification and Adaptive Control of Sampled-Data Systems, Ph.D. Dissertation, University of California, Berkeley, May 1961.