Our latest publication demonstrates how incorporating the structure and sampling characteristics of dendrites into Artificial Neural Networks can lead to more efficient, powerful, and energy-saving AI systems. Specifically, a new type of dendritic ANNs can discriminate images accurately and robustly while using much fewer parameters. This new architecture has the potential to revolutionize various fields, from healthcare to robotics, by enabling the development of more intelligent and sustainable AI solutions. The effort was led by Spyridon Chavlis, a Postdoctoral researcher at IMBB, under the supervision of Dr. Poirazi.
Dr. Yiota Poirazi and Dr. Spyridon Chavlis.
The article was published in Nature Communications and can be found at this link.
