Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification

no code implementations • 11 Apr 2021 • Konstantinos Makantasis, Alexandros Georgogiannis, Athanasios Voulodimos, Ioannis Georgoulas, Anastasios Doulamis, Nikolaos Doulamis

We hereby propose the Rank-R Feedforward Neural Network (FNN), a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters, thereby offering two core advantages compared to typical machine learning methods.

BIG-bench Machine Learning General Classification

The Generalization Error of Dictionary Learning with Moreau Envelopes

no code implementations • ICML 2018 • Alexandros Georgogiannis

Here is considered the case where $ \Phi(x) = \inf_{z \in \mathbb{R}^m} { ||x-z||_2^2 + h(||z||_2)}$ and $h$ is an even and univariate function on the real line.

Dictionary Learning Generalization Bounds +1

Robust k-means: a Theoretical Revisit

no code implementations • NeurIPS 2016 • Alexandros Georgogiannis

Over the last years, many variations of the quadratic k-means clustering procedure have been proposed, all aiming to robustify the performance of the algorithm in the presence of outliers.

Clustering Outlier Detection +1