Provable Local Learning Rule by Expert Aggregation for a Hawkes Network
Abstract
We propose a simple network of Hawkes processes as a cognitive model capable of learning to classify objects. Our learning algorithm, named HAN for Hawkes Aggregation of Neurons, is based on a local synaptic learning rule based on spiking probabilities at each output node. We were able to use local regret bounds to prove mathematically that the network is able to learn on average and even asymptotically under more restrictive assumptions.
Cite
Text
Jaffard et al. "Provable Local Learning Rule by Expert Aggregation for a Hawkes Network." Artificial Intelligence and Statistics, 2024.Markdown
[Jaffard et al. "Provable Local Learning Rule by Expert Aggregation for a Hawkes Network." Artificial Intelligence and Statistics, 2024.](https://mlanthology.org/aistats/2024/jaffard2024aistats-provable/)BibTeX
@inproceedings{jaffard2024aistats-provable,
title = {{Provable Local Learning Rule by Expert Aggregation for a Hawkes Network}},
author = {Jaffard, Sophie and Vaiter, Samuel and Muzy, Alexandre and Reynaud-Bouret, Patricia},
booktitle = {Artificial Intelligence and Statistics},
year = {2024},
pages = {1837-1845},
volume = {238},
url = {https://mlanthology.org/aistats/2024/jaffard2024aistats-provable/}
}