Lower Bounds for the Computational Power of Networks of Spiking Neurons

Neural Computation

Volumn 8, Issue 1, 1996, Pages 1-40

  Maass, Wolfgang ^a  

^a GRAZ UNIVERSITY OF TECHNOLOGY   (Austria)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0001781836     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1996.8.1.1     Document Type: Article

References (42)

1. Abeles, M. 1991. Corticonics: Neural Circuits of the Cerebral Cortex. Cambridge University Press, Cambridge, England.
2. Aertsen, A., ed. 1993. Brain Theory: Spatio-Temporal Aspects of Brain Function. Elsevier, Amsterdam.
3. Blum, L., Shub, M., and Smale, S. 1989. On a theory of computation and complexity over the real numbers: NP-completeness, recursive functions and universal machines. Bull. Am. Math. Soc. 21(1), 1-46.
4. Buhmann, J., and Schulten, K. 1986. Associative recognition and storage in a model network of physiological neurons. Biol. Cybern. 54, 319-335.
5. Churchland, P. S., and Sejnowski, T. J. 1992. The Computational Brain. MIT Press, Cambridge, MA.
6. Crair, M. C., and Bialek, W. 1990. Non-Boltzmann dynamics in networks of spiking neurons. Advances in Neural Information Processing Systems, Vol. 2, 109-116. Morgan Kaufmann, San Mateo, CA.
7. Gerstner, W. 1991. Associative memory in a network of "biological" neurons. Advances in Neural Information Processing Systems, Vol. 3, pp. 84-90. Morgan Kaufmann, San Mateo, CA.
8. Gerstner, W. 1995. Time structure of the activity in neural network models. Phys. Rev. E 51, 738-758.
9. Gerstner, W., and van Hemmen, J. L. 1994. How to describe neuronal activity: Spikes, rates, or assemblies? Advances in Neural Information Processing Systems, Vol. 6, pp. 463-470. Morgan Kaufmann, San Mateo, CA.
10. Gerstner, W., Ritz, R., and van Hemmen, J. L. 1993. A biologically motivated and analytically soluble model of collective oscillations in the cortex. Biol. Cybern. 68, 363-374.
11. Hajnal, A., Maass, W., Pudlak, P., Szegedy, M., and Turan, G. 1993. Threshold circuits of bounded depth. J. Comput. System Sci. 46, 129-154.
12. Hopcroft, J. E., and Ullman, J. D. 1979. Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, Reading, MA.
13. Horne, B. G., and Hush, D. R. 1994. Bounds on the complexity of recurrent neural network implementations of finite state machines. Advances in Neural Information Processing Systems, Vol. 6, 359-366. Morgan Kaufmann, San Mateo, CA.
14. Judd, K. T., and Aihara, K. 1993. Pulse propagation networks: A neural network model that uses temporal coding by action potentials. Neural Networks 6, 203-215.
15. Kandel, E. R., Schwartz, J. H., and Jessel, T. M. 1991. Principles of Neural Science. Prentice-Hall, Englewood Cliffs, NJ.
16. Koiran, P. 1993. A weak version of the Blum, Shub, Smale model. In Proceedings of the 34th Annual IEEE Symposium on Foundations of Computer Science, pp. 486-495. IEEE Computer Society Press, Los Alamitos, CA.
17. Lapicque, L. 1907. Recherches quantitatives sur l'excitation electrique des nerfs traitee comme une polarization. J. Physiol. Pathol. Gen. 9, 620-635.
18. Lewis, H. R., and Papadimitriou, C. H. 1981. Elements of the Theory of Computation. Prentice-Hall, Englewood Cliffs, NJ.
19. Lupanov, O. B. 1973. On circuits of threshold elements. Dokl. Akad. Nauk SSSR, Vol. 202, 1288-1291; Engl. translation in Problemy Kibernetiki, Vol. 26, 109-140.
20. Lupanov, O. B. 1973. On circuits of threshold elements. Dokl. Akad. Nauk SSSR, Vol. 202, 1288-1291; Engl. translation in Problemy Kibernetiki, Vol. 26, 109-140.
21. Maass, W. 1985. Combinatiorial lower bound arguments for deterministic and nondeterministic Turing machines. Trans. Am. Math. Soc. 292, 675-693.
22. Maass, W. 1993. Bounds for the computational power and learning complexity of analog neural nets. Proc. 25th Ann. ACM Symp. Theory Computing 335-344.
23. Maass, W. 1994a. Neural nets with superlinear VC-dimension. In Proceedings of the European Conference on Artificial Neural Networks 1994 (ICANN '94); journal version appeared in Neural Comp. 6, 875-882.
24. Maass, W. 1994a. Neural nets with superlinear VC-dimension. In Proceedings of the European Conference on Artificial Neural Networks 1994 (ICANN '94); journal version appeared in Neural Comp. 6, 875-882.
25. Maass, W. 1994b. On the Computational Complexity of Networks of Spiking Neurons (extended abstract) Tech. Rep. 393 from May 1994 of the Institutes for Information Processing Graz. Advances in Neural Information Processing Systems, Vol. 7, 183-190. MIT Press, Cambridge, MA.
26. Maass, W. 1994b. On the Computational Complexity of Networks of Spiking Neurons (extended abstract) Tech. Rep. 393 from May 1994 of the Institutes for Information Processing Graz. Advances in Neural Information Processing Systems, Vol. 7, 183-190. MIT Press, Cambridge, MA.
27. Maass, W. 1995a. Vapnik-Chervonenkis dimension of neural nets. In Handbook of Brain Theory and Neural Networks, pp. 1000-1003, M.A. Arbib, ed., MIT Press, Cambridge, MA.
28. Maass, W. 1995b. Analog computations on networks of spiking neurons (extended abstract); appears in Proc. 7th Italian Workshop on Neural Nets 1995, World Scientific Press.
29. Maass, W. 1995b. Analog computations on networks of spiking neurons (extended abstract); appears in Proc. 7th Italian Workshop on Neural Nets 1995, World Scientific Press.
30. Maass, W. 1995c. Upper bounds for the computational power of networks of spiking neurons (in preparation).
31. Maass, W. 1995d. On the computational power of noisy spiking neurons. Tech. Rep. 412 (May 1995) of the Institutes for Information Processing, Graz, Austria; appears in Advances in Neural Information Processing Systems, Vol. 8 (1996).
32. Maass, W. 1995d. On the computational power of noisy spiking neurons. Tech. Rep. 412 (May 1995) of the Institutes for Information Processing, Graz, Austria; appears in Advances in Neural Information Processing Systems, Vol. 8 (1996).
33. Maass, W., and Ruf, B. 1995. Consequenes of the shape of postsynaptic potentials for the computational power of networks of spiking neurons; appears in Proc. International Conference on Artificial Neural Networks (ICANN '95), Paris.
34. Maass, W., and Ruf, B. 1995. Consequenes of the shape of postsynaptic potentials for the computational power of networks of spiking neurons; appears in Proc. International Conference on Artificial Neural Networks (ICANN '95), Paris.
35. Maass, W., Schnitger, G., and Szemeredi, E. 1987. Two tapes are better than one for off-line Turing machines. Proc. 19th Ann. ACM Symp. Theory Computing 94-100.
36. Murray, A., and Tarassenko, L. 1994. Analogue Neural VLSI: A Pulse Stream Approach. Chapman & Hall, London.
37. Siegelmann, H. T., and Sontag, E. D. 1992. On the computational power of neural nets. Proc. 5th ACM-Workshop Comp. Learning Theory 440-449.
38. Tuckwell, H. C. 1988. Introduction to Theoretical Neurobiology, Vols. 1 and 2. Cambridge University Press, Cambridge, England.
39. Valiant, L. G. 1994. Circuits of the Mind. Oxford University Press, Oxford, England.
40. Vapnik, V. N., and Chervonenkis, A.Y. 1971. On the uniform convergence of relative frequencies of events to their probabilities. Theory Prob. Appl. 16, 264-280.
41. von der Malsburg, C., and Schneider, W. 1986. A neural cocktail-party processor. Biol. Cybern. 54, 29-40.
42. Watts, L. 1994. Event-driven simulation of networks of spiking neurons. Advances in Neural Information Processing Systems, Vol. 6, pp. 927-934. Morgan Kaufmann, San Mateo, CA.