Vapnik-Chervonenkis dimension of recurrent neural networks

Baum, 1989, What size net gives valid generalization?, Neural Comput., 1, 151, 10.1162/neco.1989.1.1.151

Bengio, 1996

Blumer, 1989, Learnability and the Vapnik-Chervonenkis Dimension, J. ACM, 36, 929, 10.1145/76359.76371

Cover, 1968, Capacity problems for linear machines, 283

Dasgupta, 1996, Sample complexity for learning recurrent perceptron mappings, IEEE Trans. Inform. Theory, 42, 1479, 10.1109/18.532888

1996, 204

Giles, 1990, Higher order recurrent networks and grammatical inference

Goldberg, 1995, Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers, Machine Learning, 18, 131, 10.1007/BF00993408

Grossberg, 1987, 2 vols

Hopfield, 1982, Neural networks and physical systems with emergent computational abilities, 79, 2554

Karpinski, 1997, Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks, J. Comput. System Sci., 54, 169, 10.1006/jcss.1997.1477

Koiran, 1997, Neural networks with quadratic VC dimension, J. Comput. System Sci., 54, 190, 10.1006/jcss.1997.1479

Polycarpou, 1992, Neural networks and on-line approximators for adaptive control, 793

Siegelmann, 1995, On the computational power of neural nets, J. Comput. System Sci., 50, 132, 10.1006/jcss.1995.1013

Siegelmann, 1994, Analog computation, neural networks, and circuits, Theoret. Comput. Sci., 131, 331, 10.1016/0304-3975(94)90178-3

Sontag, 1990

Sontag, 1992, Neural nets as systems models and controllers, 73

Sontag, 1992, Feedforward nets for interpolation and classification, J. Comput. System Sci., 45, 20, 10.1016/0022-0000(92)90039-L

Zador, 1996, VC dimension of an integrate-and-fire neuron model, Neural Comput., 8, 611, 10.1162/neco.1996.8.3.611