paper-with-me

Papers

Towards a mathematical understanding of learning from few examples with nonlinear feature maps

2022-11-07 · Oliver J. Sutton, Alexander N. Gorban, Ivan Y. Tyukin

We consider the problem of data classification where the training set consists of just a few data points. We explore this phenomenon mathematically and reveal key relationships between the geometry of an AI model's feature space, the structure of the underlying data distributions, and the model's generalisation capabilities. The main thrust of our analysis is to reveal the influence on the model's generalisation capabilities of nonlinear feature transformations mapping the original data into high, and possibly infinite, dimensional spaces.

📄 PDF Abstract BibTeX arXiv:2211.03607

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search

2022-05-26 · Fangzheng Sun, Yang Liu, Jian-Xun Wang, Hao Sun

Nonlinear dynamics is ubiquitous in nature and commonly seen in various science and engineering disciplines. Distilling analytical expressions that govern nonlinear dynamics from limited data remains vital but challengin…

On the Spectrum of Random Features Maps of High Dimensional Data

2018-05-30 · ICML 2018 7 · Zhenyu Liao, Romain Couillet

Random feature maps are ubiquitous in modern statistical machine learning, where they generalize random projections by means of powerful, yet often difficult to analyze nonlinear operators. In this paper, we leverage the…

BIG-bench Machine LearningVocal Bursts Intensity Prediction

Learning from few examples with nonlinear feature maps

2022-03-31 · Ivan Y. Tyukin, Oliver Sutton, Alexander N. Gorban

In this work we consider the problem of data classification in post-classical settings were the number of training examples consists of mere few data points. We explore the phenomenon and reveal key relationships between…

Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time

2020-01-01 · ICML 2020 1 · Zahra Monfared, Daniel Durstewitz

Recurrent neural networks (RNN) as used in machine learning are commonly formulated in discrete time, i.e. as recursive maps. This brings a lot of advantages for training models on data, e.g. for the purpose of time seri…

BIG-bench Machine LearningNumerical IntegrationTime SeriesTime Series Analysis+2

Optimization-Based MCMC Methods for Nonlinear Hierarchical Statistical Inverse Problems

2020-02-15 · Johnathan Bardsley, Tiangang Cui

In many hierarchical inverse problems, not only do we want to estimate high- or infinite-dimensional model parameters in the parameter-to-observable maps, but we also have to estimate hyperparameters that represent criti…