Affordable Access

Towards incremental deep learning: multi-level change detection in a hierarchical recognition architecture

Authors
  • Hecht, Thomas
  • Gepperth, Alexander
Publication Date
Jan 01, 2016
Source
HAL-UPMC
Keywords
Language
English
License
Unknown
External links

Abstract

We present a trainable hierarchical architecture capable of detecting newness (or outliers) at all hierarchical levels. This contribution paves the way for deep neural architectures that are able to learn in an incremental fashion, for which the ability to detect newness is an indispensable prerequisite. We verify the ability to detect newness by conducting experiments on the MNIST database, where we introduce either localized changes, by adding noise to a small patch of the input, or global changes, by changing the global arrangement of local patterns which is not detectable at the local level.

Report this publication

Statistics

Seen <100 times