Topographic mAP Formation by Silicon Growth Cones
Abstract
We describe a self-configuring neuromorphic chip that uses a model of activity-dependent axon remodeling to automatically wire topographic maps based solely on input correlations. Axons are guided by growth cones, which are modeled in analog VLSI for the first time. Growth cones migrate up neurotropin gradients, which are represented by charge diffusing in transistor channels. Virtual axons move by rerouting address-events. We refined an initially gross topographic projection by simulating retinal wave input.
Cite
Text
Taba and Boahen. "Topographic mAP Formation by Silicon Growth Cones." Neural Information Processing Systems, 2002.Markdown
[Taba and Boahen. "Topographic mAP Formation by Silicon Growth Cones." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/taba2002neurips-topographic/)BibTeX
@inproceedings{taba2002neurips-topographic,
title = {{Topographic mAP Formation by Silicon Growth Cones}},
author = {Taba, Brian and Boahen, Kwabena A.},
booktitle = {Neural Information Processing Systems},
year = {2002},
pages = {1163-1170},
url = {https://mlanthology.org/neurips/2002/taba2002neurips-topographic/}
}