Strong Universal Consistency of Neural Network Classifiers
By Andras Farago, Gábor Lugosi. 1993
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Bernhard Schölkopf
- Anirudh Goyal
- Francesco Locatello
- Sergey Levine
- Ruslan Salakhutdinov
- Quoc V. Le
- Dacheng Tao
Citations in the corpus
- Toward Causal Representation Learning (2021, background): “Such algorithms do exist, for instance, nearest neighbor classi-fiers, support vector machines, and neural networks [67], [221], [239], [257].”
- Towards Causal Representation Learning (2021, background): “Such algorithms do exist, for instance, nearest neighbor classifiers, support vector machines, and neural networks [257, 217, 239, 66].”
- Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference (2001, background): “Similarly, smoothness conditions must be satisfied for the results of [16].”
- Universal approximation bounds for superpositions of a sigmoidal function (1993, background): “The implication of polynomial bounds on C/, B, as a consequence of the bound 2C /, B / yin from Theorem 1, is that a polynomial rather than an exponential number of nodes n is sufficient for accurate approximation by sigmoidal networks.”
- Learning Summary Statistic for Approximate Bayesian Computation via Deep Neural Network (2015, background): “approximation properties of DNNs remains an important open problem (Faragó and Lugosi (1993); Sutskever and Hinton (2008); Le Roux and Bengio (2010)).”