Analog versus Discrete Neural Networks

Neural Computation

Volumn 8, Issue 4, 1996, Pages 805-818

  DasGupta, Bhaskar ^a   Schnitger, Georg ^b  

^a UNIVERSITY OF WATERLOO   (Canada)

^b GOETHE UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ANALOG COMPUTER; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPARATIVE STUDY; MATHEMATICS; NERVE CELL;

COMPUTERS, ANALOG; MATHEMATICS; NEURAL NETWORKS (COMPUTER); NEURONS;

EID: 0030585103     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1996.8.4.805     Document Type: Article

References (14)

1. Boppana, R., and Sipser, M. 1990. The complexity of finite functions. In Handbook of Theoretical Computer Science: Algorithms and Complexity, J. van Leeuwen, ed. MIT Press, Cambridge, MA.
2. Dasgupta, B., and Schnitger, G. 1993. The power of approximating: A comparison of activation functions. In Advances in Neural Information Processing Systems 5, C. L. Giles, S. J. Hanson, and J. D. Cowan, eds., pp. 615-622, Morgan Kaufmann, San Mateo, CA.
3. Goldmann, M., and Hastad, J. 1991. On the power of small-depth threshold circuits. Comp. Complex., 1(2), 113-129.
4. Hajnal, A., Maass, W., Pudlak, P., Szegedy, M., and Turan, G. 1987. Threshold circuits of bounded depth. Proc. 28th IEEE Symp. Found. Computer Sci., 99-110.
5. Höffgen, K-U. 1993. Computational limitations on training sigmoidal neural networks. Inform. Process. Lett., 46, 269-274.
6. Maass, W. 1993. Bounds for the computational power and learning complexity of analog neural nets. Proc. 25th ACM Symp. Theory Comput., 335-344.
7. Maass, W., Schnitger, G., and Sontag, E. D. 1991. On the computational power of sigmoid versus boolean threshold circuits. Proc. 32nd Annu. Symp. Found. Computer Sci. 767-776.
8. MacIntyre, A., and Sontag, E. D. 1993. Finiteness results for sigmoidal 'neural' networks. Proc. 25th Annu. Symp. Theory Comput. 325-334.
9. Razborov, A. A. 1987. Lower bounds on the size of bounded depth networks over a complete basis with logical addition. Math. Notes Acad. Sci. USSR 41(4), 333-338.
10. Reif, J. H. 1987. On threshold circuits and polynomial computation. Proc. 2nd Annu. Struct. Complexity Theory 118-123.
11. Sontag, E. D. 1990. Comparing sigmoids and heavisides. In Proc. Conf. Inform. Sci. Syst. 654-659.
12. Wegener, I. 1987. The Complexity of Boolean Functions. Wiley-Teubner Series in Computer Science, New York.
13. Wegener, I. 1991. The complexity of the parity function in unbounded fan-in, unbounded depth circuits. Theor. Comp. Sci. 85, 155-170.
14. Zhang, X-D. 1992. Complexity of neural network learning in the real number model, preprint, Computer Science Department, University of Massachusetts.