1Salk Institute, 10010 N. Torrey Pines Rd., La Jolla, CA 92037 USA
2Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540 USA
Tóm tắt
We compute the VC dimension of a leaky integrate-and-fire neuron model. The VC dimension quantifies the ability of a function class to partition an input pattern space, and can be considered a measure of computational capacity. In this case, the function class is the class of integrate-and-fire models generated by varying the integration time constant T and the threshold θ, the input space they partition is the space of continuous-time signals, and the binary partition is specified by whether or not the model reaches threshold at some specified time. We show that the VC dimension diverges only logarithmically with the input signal bandwidth N. We also extend this approach to arbitrary passive dendritic trees. The main contributions of this work are (1) it offers a novel treatment of computational capacity of this class of dynamic system; and (2) it provides a framework for analyzing the computational capabilities of the dynamic systems defined by networks of spiking neurons.
Từ khóa
Tài liệu tham khảo
10.1162/neco.1989.1.3.312
Bartlett P. L., 1994, NJ, 299
10.1162/neco.1989.1.1.151
Haussler D., 1994, NJ, 67
Koch C., 1982, Proc. Royal Soc. Lotidori B, 298, 227
