DEMUD: Discovery through Eigenbasis Modeling of Uninteresting Data(NPO-48877-1)
data servers processing and handling
DEMUD: Discovery through Eigenbasis Modeling of Uninteresting Data
(NPO-48877-1)
Overview
We have developed a machine learning solution called DEMUD (Discovery through Eigenbasis Modeling of Uninteresting Data). DEMUD works by building a model U of the uninteresting class and then identifying items that are maximally anomalous (and therefore likely to be interesting) with respect to that model.
Notes: https://download.jpl.nasa.gov/ops/request/index.cfm, request software
Software Details
Category
Data Servers Processing and Handling
Reference Number
NPO-48877-1
Release Type
Open Source
Operating System