GDM: Growing Dual-Memory Self-Organizing Networks

Batch and incremental learning (with memory replay).

gdm_demo.py runs a demo on the Iris dataset as example.

You can export, import, and plot trained networks using gtls.py

For more demos, check out the GWR Toolbox: https://github.com/giparisi/gwr-tb

Reference:

• Parisi, G.I., Tani, J., Weber, C., Wermter, S. (2018) Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization. arXiv:1805.10966