2 papers
cs.LG2016
Expected Similarity Estimation for Large-Scale Batch and Streaming Anomaly Detection
Markus Schneider, Wolfgang Ertel, Fabio Ramos
We present a novel algorithm for anomaly detection on very large datasets and data streams. The method, named EXPected Similarity Estimation (EXPoSE), is kernel-based and able to e…
cs.LG2015
Constant Time EXPected Similarity Estimation using Stochastic Optimization
Markus Schneider, Wolfgang Ertel, Günther Palm
A new algorithm named EXPected Similarity Estimation (EXPoSE) was recently proposed to solve the problem of large-scale anomaly detection. It is a non-parametric and distribution f…