Dynamic on-line clustering and state extraction: An approach to symbolic learning

Neural Networks

Volumn 11, Issue 1, 1998, Pages 53-64

  Das, Sreerupa ^a   Mozer, Michael ^b  

^a LUCENT TECHNOLOGIES   (United States)

^b UCB 450   (United States)

Author keywords

Differentiable state extraction; DOLCE; Finite state automata; On line clustering; Recurrent network

Indexed keywords

COMPUTER ARCHITECTURE; COMPUTER SIMULATION; FINITE AUTOMATA; LEARNING SYSTEMS; MATHEMATICAL MODELS; ONLINE SYSTEMS; PROBABILITY; SEQUENTIAL MACHINES; STATE SPACE METHODS;

DIFFERENTIABLE STATE EXTRACTION; DYNAMIC ONLINE CLUSTERING; FINITE STATE MACHINES (FSM);

RECURRENT NEURAL NETWORKS;

ARTICLE; BEHAVIOR; LEARNING; NERVE CELL NETWORK; NOISE; PRIORITY JOURNAL; PROBABILITY; SPACE;

EID: 0031915593     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(97)00113-5     Document Type: Article

References (19)

1. Ball, G., & Hall, D. (1966). ISODATA: a novel method of data analysis and pattern classification. Technical report. Menlo Park, CA: Stanford Research Institute.
2. Das S., Das R. Induction of discrete state-machine by stabilizing a continuous recurrent network using clustering. Computer Science and Informatics. 21(2):1991;35-40. Special Issue on Neural Computing.
3. Das, S., & Mozer, M. (1994). A hybrid clustering/gradient descent architecture for finite state machine induction. In J. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in Neural Information Processing Systems, Vol. 6. San Mateo, CA: Morgan Kaufmann, pp. 19-26.
4. Elman J. Finding structure in time. Cognitive Science. 14(2):1990;179-212.
5. Forgy E. Cluster analysis of multivariate data: efficiency versus interpretability of classifications. Biometrics. 21:1965;768.
6. Giles C., Miller C.B., Chen H., Sun G., Lee Y. Learning and extracting finite state automata with second-order recurrent neural network. Neural Computation. 4(4):1992;393-405.
7. Gori, M., Maggini, M., & Soda, G. (1993) Insertion of finite state automata into recurrent radial basis function networks. Technical Report DSI 17/93. Florence, Italy: Department of Systems and Informatics, University of Florence.
8. McMillan, C., Mozer, M., & Smolensky, P. (1992). Rule induction through integrated symbolic and subsymbolic processing. In J. Moody, S. Hanson, & R. Lippmann (Eds.), Advances in Neural Information Processing Systems, Vol. 4. San Mateo, CA: Morgan Kaufmann, pp. 969-967.
9. Mozer M., Bachrach J. Discovering the structure of a reactive environment by exploration. Neural Computation. 2(4):1990;447-457.
10. Mozer, M., & Das, S. (1993). A connectionist symbol manipulator that discovers the structure of context-free languages. In C. Giles, S. Hanson, & J. Cowan (Eds.), Advances in Neural Information Processing Systems, Vol. 5. San Mateo, CA: Morgan Kaufmann, pp. 863-870.
11. Nowlan S., Hinton G. Simplifying neural networks by soft weight-sharing. Neural computation. 4(4):1992;473.
12. Pollack J. The induction of dynamical recognizers. Machine Learning. 7(2/3):1991;123-148.
13. Rumelhart, D., Hinton, G., & Williams, R. (1996). Learning internal representations by error propagation. In Parallel distributed processing, Chapter 8. Cahmbridge, MA: MIT Press.
14. Schütze, H. (1993). Word space. In C. Giles, S. Hanson, & J. Cowan (Eds.), Advances in Neural Information Processing Systems, Vol. 5. San Mateo, CA: Morgan Kaufmann, pp. 895-902.
15. Servan-Schreiber D., Cleeremans A., McClelland J. Graded state machines: the representation of temporal contingencies in simple recurrent network. Machine Learning. 7(2/3):1991;161-193.
16. Tomita, M. (1982). Dynamic construction of finite-state automata from examples using hill-climbing. In Proceedings of the Fourth Annual Conference of the Cognitive Science Society, pp. 105-108.
17. Towell, G., & Shavlik, J. (1992). Interpretation of artificial neural networks: mapping knowledge-based neural networks into rules. In D. Touretzky (Ed.), Advances in Neural Information Processing Systems, Vol. 2, San Mateo, CA: Morgan Kaufmann, pp. 977-984.
18. Watrous, R., & Kuhn, G. (1992). Induction of finite state languages using second-order recurrent networks. In J. Moody, S. Hanson, & R. Lippmann (Eds.), Advances in Neural Information Processing Systems, Vol. 4. San Mateo, CA: Morgan Kaufmann, pp. 309-316.
19. Zeng Z., Goodman R., Smythe P. Learning finite state machines with self-clustering recurrent networks. Neural Computation. 5(6):1993;976-990.