Real-time machine learning in embedded software and hardware platforms

This paper describes on-going research work into real-time machine learning using embedded software and reconfigurable hardware. The main focus of the work is to develop real-time incremental learning methods particularly targeted at demonstration in mobile robot environments. Three main areas are described. The first represents reactive robot navigation knowledge using a novel frequency table technique whose memory requirement is known a priori. The second area investigates a Genetic Algorithm (GA) method that combines planning and reactive approaches to allow navigation to proceed even in the face of time constraints. In the third area we are developing novel hardware-based machine learning systems suitable for implementation in reconfigurable platforms.

[1]  Stefano Caselli,et al.  Experiments in robust bistatic sonar object classification for local environment mapping , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[2]  Paul E. Utgoff,et al.  Decision Tree Induction Based on Efficient Tree Restructuring , 1997, Machine Learning.

[3]  Günter Rudolph,et al.  Convergence analysis of canonical genetic algorithms , 1994, IEEE Trans. Neural Networks.

[4]  Bruno Sareni,et al.  Fitness sharing and niching methods revisited , 1998, IEEE Trans. Evol. Comput..

[5]  D. Mulvaney,et al.  Efflcient incremental decision tree generation for embedded applications , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[6]  A. Vlahou,et al.  Diagnosis of Ovarian Cancer Using Decision Tree Classification of Mass Spectral Data , 2003, Journal of biomedicine & biotechnology.

[7]  Zhang Ling,et al.  Research on the Mechanism of Genetic Algorithms , 2000 .

[8]  J. Ross Quinlan,et al.  Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .

[9]  Ian P. W. Sillitoe,et al.  Becoming incrementally reactive: on-line learning of an evolving decision tree array for robot navigation , 1999, Robotica.

[10]  J. W. Hauser,et al.  Sensor data processing using genetic algorithms , 2000, Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144).

[11]  Shin'ichi Wakabayashi,et al.  Genetic algorithm accelerator GAA-II , 2000, ASP-DAC '00.

[12]  H.S. Abdel-Aty-Zohdy,et al.  A hardware implementation of genetic algorithms for measurement characterization , 2002, 9th International Conference on Electronics, Circuits and Systems.

[13]  Zbigniew Michalewicz,et al.  Adaptive evolutionary planner/navigator for mobile robots , 1997, IEEE Trans. Evol. Comput..

[14]  Paul E. Utgoff,et al.  ID5: An Incremental ID3 , 1987, ML.

[15]  J. Ross Quinlan,et al.  Decision trees and decision-making , 1990, IEEE Trans. Syst. Man Cybern..

[16]  G. H. Shah Hamzei,et al.  Implementation of an Intelligent Control System Using Fuzzy ITI , 2000, Neural Computing & Applications.

[17]  Paul E. Utgoff,et al.  Improved Training Via Incremental Learning , 1989, ML.

[18]  Haji Izham Haji Zainal Abidin,et al.  The fuzzy decision tree application to a power system problem , 2004 .

[19]  Deborah R. Carvalho,et al.  A hybrid decision tree/genetic algorithm method for data mining , 2004, Inf. Sci..

[20]  Yohanan Arzi,et al.  Operating an FMC by a decision-tree-based adaptive production control system , 2000 .

[21]  Chao-Ton Su,et al.  Intelligent scheduling controller for shop floor control systems: A hybrid genetic algorithm/decision tree learning approach , 2003 .

[22]  Prabhas Chongstitvatana,et al.  A hardware implementation of the Compact Genetic Algorithm , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[23]  Ashok Samal,et al.  HGA: A Hardware-Based Genetic Algorithm , 1995, Third International ACM Symposium on Field-Programmable Gate Arrays.