Correction of AI systems by linear discriminants: probabilistic foundations
From MaRDI portal
Publication:2200569
big dataerror correctionmeasure concentrationblessing of dimensionalitylinear discriminantnon-iterative learning
Probability distributions: general theory (60E05) Learning and adaptive systems in artificial intelligence (68T05) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Computational aspects of data analysis and big data (68T09) Geometric probability and stochastic geometry (60D05) Inequalities; stochastic orderings (60E15) General topics in artificial intelligence (68T01)
Abstract: Artificial Intelligence (AI) systems sometimes make errors and will make errors in the future, from time to time. These errors are usually unexpected, and can lead to dramatic consequences. Intensive development of AI and its practical applications makes the problem of errors more important. Total re-engineering of the systems can create new errors and is not always possible due to the resources involved. The important challenge is to develop fast methods to correct errors without damaging existing skills. We formulated the technical requirements to the 'ideal' correctors. Such correctors include binary classifiers, which separate the situations with high risk of errors from the situations where the AI systems work properly. Surprisingly, for essentially high-dimensional data such methods are possible: simple linear Fisher discriminant can separate the situations with errors from correctly solved tasks even for exponentially large samples. The paper presents the probabilistic basis for fast non-destructive correction of AI systems. A series of new stochastic separation theorems is proven. These theorems provide new instruments for fast non-iterative correction of errors of legacy AI systems. The new approaches become efficient in high-dimensions, for correction of high-dimensional systems in high-dimensional world (i.e. for processing of essentially high-dimensional data by large systems).
Recommendations
- Fast construction of correcting ensembles for legacy artificial intelligence systems: algorithms and a case study
- One-trial correction of legacy AI systems and stochastic separation theorems
- Stochastic separation theorems
- General stochastic separation theorems with optimal bounds
- Blessing of dimensionality: mathematical foundations of the statistical physics of data
Cites work
- scientific article; zbMATH DE number 3126094 (Why is no real title available?)
- scientific article; zbMATH DE number 1182755 (Why is no real title available?)
- scientific article; zbMATH DE number 1391397 (Why is no real title available?)
- Approximation of the Sphere by Polytopes having Few Vertices
- Approximation with random bases: pro et contra
- Blessing of dimensionality: mathematical foundations of the statistical physics of data
- Concentration of measure and isoperimetric inequalities in product spaces
- Concentration property on probability spaces.
- Convexity. An analytic viewpoint
- Deep learning
- Fast kernel classifiers with online and active learning
- From Brunn-Minkowski to Brascamp-Lieb and to logarithmic Sobolev inequalities
- Geometry of isotropic convex bodies
- Interpolating thin-shell and sharp large-deviation estimates for isotropic log-concave measures
- Is the \(k\)-NN classifier in high dimensions affected by the curse of dimensionality?
- Isoperimetric and analytic inequalities for log-concave probability measures
- Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing
- On the Geometry of Log-Concave Probability Measures with Bounded Log-Sobolev Constant
- On the mathematical foundations of learning
- On the shape of the convex hull of random points
- Probabilistic lower bounds for approximation by shallow perceptron networks
- Quasiorthogonal dimension of Euclidean spaces
- Small ball probability estimates for log-concave measures
- Stochastic separation theorems
- The geometry of logconcave functions and sampling algorithms
- Training a Support Vector Machine in the Primal
- Universal approximation bounds for superpositions of a sigmoidal function
Cited in
(10)- Scrutinizing XAI using linear ground-truth data with suppressor variables
- Fast construction of correcting ensembles for legacy artificial intelligence systems: algorithms and a case study
- One-trial correction of legacy AI systems and stochastic separation theorems
- Approximation of classifiers by deep perceptron networks
- Machine learning approach to the Floquet-Lindbladian problem
- General stochastic separation theorems with optimal bounds
- Coping with AI errors with provable guarantees
- Blessing of dimensionality at the edge and geometry of few-shot learning
- scientific article; zbMATH DE number 5367516 (Why is no real title available?)
- Stochastic separation theorems
This page was built for publication: Correction of AI systems by linear discriminants: probabilistic foundations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2200569)
