TY  - EDBOOK
AB  - In this paper, an extension of the unsupervised topology-learning TopoART neural network is presented. Like TopoART, it is capable of stable incremental on-line clustering of real-valued data. However, it incorporates temporal information in such a way that consecutive input vectors with a low distance in the input space are summarised to episode-like clusters. Inspired by natural memory systems, we propose two recall methods enabling the selection and retrieval of these episodes. They are demonstrated at the example of a video stream recorded in a natural environment.
DA  - 2012
KW  - Adaptive Resonance Theory
KW  - On-line learning
KW  - TopoART
KW  - Episodic memory
KW  - Incremental learning
KW  - Clustering
KW  - Neural networks
LA  - eng
PY  - 2012
TI  - Episodic Clustering of Data Streams Using a Topology-Learning Neural Network
UR  - https://nbn-resolving.org/urn:nbn:de:0070-pub-25192218
Y2  - 2024-11-22T03:12:38
ER  -