Efficient Dictionary Learning with Sparseness-Enforcing Projections

no code implementations • 16 Apr 2016 • Markus Thom, Matthias Rapp, Günther Palm

This theory is applied in an original algorithm called Easy Dictionary Learning (EZDL), which learns dictionaries with a simple and fast-to-compute Hebbian-like learning rule.

Denoising Dictionary Learning

Sparse Activity and Sparse Connectivity in Supervised Learning

no code implementations • 28 Mar 2016 • Markus Thom, Günther Palm

In the theoretical part of this paper, a comprehensive theory for such a projection is developed.

Classification General Classification +1

Constant Time EXPected Similarity Estimation using Stochastic Optimization

no code implementations • 17 Nov 2015 • Markus Schneider, Wolfgang Ertel, Günther Palm

In this work we improve the linear computational complexity and show that an $\epsilon$-accurate model can be estimated in constant time, which has significant implications for large-scale learning problems.

Anomaly Detection Stochastic Optimization