Maximally fault tolerant neural networks

By Chalapathy Neti, Michael H. Schneider, E. Young. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Compare perturbation tolerance conditions (Minai and Williams, 1994; Murray and Edwards, 1993; Neti et al., 1992; Matsuoka, 1992; Bishop, 1993; Kerlirzin and Vallet, 1993; Carter et al., 1990).”
Flat Minima (1997, unknown): “…8 ij : v ij = w ij g. Flatness condition 1 is a \robustness condition" (or \fault tolerance condition", or \perturbation tolerance condition" { see, e.g., Minai & Williams, 1994; Murray & Edwards, 1993; Neti et al., 1992; Matsuoka, 1992; Bishop, 1993; Kerlirzin & Vallet, 1993; Carter et al., 1990).”
Relating Adversarially Robust Generalization to Flat Minima (2021, background): “It has been studied in early works [66, 15, 22], obtaining fault tolerance e., the corresponding eigenvector).”
When Neurons Fail - Technical Report (2016, background): “To our knowledge there has been one single attempt to theoretically formulate such a constraint [31], but it only minimizes the effect of the crash of a single neuron.”
On the Robustness of a Neural Network (2017, background): “…of our knowledge, the work on failures at the level of individual neurons has been mostly experimental [27], [28], [29], [30], [31], or, when it included a theoretical analysis, it focused on bounding the effect of the lost of a single neuron [32] or the cost in terms of additional learning [26].”
When Neurons Fail (2017, background): “To our knowledge, there has been one single attempt to theoretically formulate such an optimization problem [36], but it only minimizes the effect of the crash of a single neuron.”