High-dimensional separability for one- and few-shot learning

Abstract

This work is driven by a practical question: corrections of Artificial Intelligence (AI) errors. These corrections should be quick and non-iterative. To solve this problem without modification of a legacy AI system, we propose special `external' devices, correctors. Elementary correctors consist of two parts, a classifier that separates the situations with high risk of error from the situations in which the legacy AI system works well and a new decision for situations with potential errors. Input signals for the correctors can be the inputs of the legacy AI system, its internal signals, and outputs. If the intrinsic dimensionality of data is high enough then the classifiers for correction of small number of errors can be very simple. According to the blessing of dimensionality effects, even simple and robust Fisher's discriminants can be used for one-shot learning of AI correctors. Stochastic separation theorems provide the mathematical basis for this one-short learning. However, as the number of correctors needed grows, the cluster structure of data becomes important and a new family of stochastic separation theorems is required. We refuse the classical hypothesis of the regularity of the data distribution and assume that the data can have a fine-grained structure with many clusters and peaks in the probability density. New stochastic separation theorems for data with fine-grained structure are formulated and proved. The multi-correctors for granular data are proposed. The advantages of the multi-corrector technology were demonstrated by examples of correcting errors and learning new classes of objects by a deep convolutional neural network on the CIFAR-10 dataset. The key problems of the non-classical high-dimensional data analysis are reviewed together with the basic preprocessing steps including supervised, semi-supervised and domain adaptation Principal Component Analysis.

arXiv commentCorrected and restructured version with some extensions

References in corpus (17)

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Principal Graphs and Manifolds
• Principal manifolds and graphs in practice: from molecular biology to dynamical systems
• Approximation with Random Bases: Pro et Contra
• Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem
• Blessing of dimensionality: mathematical foundations of the statistical physics of data
• Robust And Scalable Learning Of Complex Dataset Topologies Via Elpigraph
• Correction of AI systems by linear discriminants: Probabilistic foundations
• The unreasonable effectiveness of small neural ensembles in high-dimensional brain
• Selection theorem for systems with inheritance
• Stochastic Separation Theorems
• High--Dimensional Brain in a High-Dimensional World: Blessing of Dimensionality
• Fractional norms and quasinorms do not help to overcome the curse of dimensionality
• On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems
• The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures
• General stochastic separation theorems with optimal bounds
• Blessing of dimensionality at the edge

Cited by in corpus (3)

• Situation-based memory in spiking neuron-astrocyte network
• The Feasibility and Inevitability of Stealth Attacks
• The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning