/gwr-tb

GWR Toolbox

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

gwr-tb :: GWR Toolbox

This repository contains 3 types of extensions of the Grow-When-Required (GWR) self-organizing neural network by Marsland et al. (2002).

Use demo files for off-the-shelf functionalities with the Iris dataset.

You can create, train, test, plot, import and export GWR networks.


Associative GWR (AGWR; Parisi et al., 2015) - Standard GWR extended with associative labelling.


GammaGWR (Parisi et al., 2017) - GWR with temporal context (Gamma memory).


Episodic GWR (Parisi et al., 2018) - GWR with temporal context, temporal connections, and task-relavant learning modulation.


References:

  • [Parisi et al., 2018] Parisi, G.I., Tani, J., Weber, C., Wermter, S. (2017) Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization. Frontiers in Neurorobotics, in press.

  • [Parisi et al., 2017] Parisi, G.I., Tani, J., Weber, C., Wermter, S. (2017) Lifelong Learning of Human Actions with Deep Neural Network Self-Organization. Neural Networks, 96:137-149.

  • [Parisi et al., 2015] Parisi, G.I., Weber, C., Wermter, S. (2015) Self-Organizing Neural Integration of Pose-Motion Features for Human Action Recognition. Frontiers in Neurorobotics, 9(3).

  • [Marsland et al., 2002] Marsland, S., Shapiro, J., and Nehmzow, U. (2002). A self-organising network that grows when required. Neural Networks, 15(8-9):1041-1058.