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

Thomas Hecht (1) , Alexander Gepperth (1, 2)

1 RV - Robotique et Vision
2 Flowers - Flowing Epigenetic Robots and Systems

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.

Domaines: Apprentissage [cs.LG]

Thomas Hecht, Alexander Gepperth. Towards incremental deep learning: multi-level change detection in a hierarchical recognition architecture. European Symposium on Artificial Neural Networks (ESANN), 2016, Bruges, Belgium. ⟨hal-01418132⟩