VC dimension bounds for networks of spiking neurons (1999) [2 citations — 2 self]
by Michael Schmitt
In Proceedings of the 7th European Symposium on Artificial Neural Networks ESANN 99
http://www.cis.tu-graz.ac.at/igi/maass/96.ps.gz
Add To MetaCart
Abstract:
Abstract. We calculate bounds on the VC dimension and pseudo dimension for networks of spiking neurons. The connections between network nodes are parameterized by transmission delays and synaptic weights. We provide bounds in terms of network depth and number of connections that are almost linear. For networks with few layers this yields better bounds than previously established results for networks of unrestricted depth.
Citations
| 86 | Networks of Spiking Neurons: The Third Generation of Neural Network Models. Neural Networks 10(9):1659 – Maass - 1997 |
| 81 | A Theory of Learning and Generalization – Vidyasagar - 1997 |
| 80 | Spiking neurons – Gerstner - 1998 |
| 28 | Paradigms for computing with spiking neurons – Maass - 1999 |
| 11 | On the complexity of learning for a spiking neuron – Maass, Schmitt - 1997 |
| 9 | Pulse-based computation in VLSI neural networks – Murray - 1999 |
| 3 | On the complexity of computing and learning with networks of spiking neurons – Maass, Schmitt - 1998 |
| 1 | Complexity of Boolean computations for a spiking neuron – Schmitt - 1998 |
| 1 | On the complexity oflearning for a spiking neuron – Maass, Schmitt - 1997 |
