Towards a More Sustainable Future for AI:
Led by Dr. Chavlis, our research, published in @naturecomms.bsky.social, demonstrates how incorporating dendritic features into Artificial Neural Networks (ANNs) can significantly improve their efficiency and performance.
www.nature.com/articles/s41...
Artificial neural networks, central to deep learning, are powerful but energy-consuming and prone to overfitting. The authors propose a network design inspired by biological dendrites, which offe...