Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning

arXiv:2404.03708v1 Announce Type: cross
Abstract: Artificial neural networks (ANNs) are at the core of most Deep learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient manner, DL algorithms require a large number of trainable parameters, making them energy-intensive and prone to overfitting. Here, we show that a new ANN architecture that incorporates the structured connectivity and restricted sampling properties of …

abstract algorithms and natural language processing anns artificial artificial neural networks arxiv autonomous autonomous driving brains core cs.lg cs.ne deep learning driving however image image recognition language language processing natural natural language natural language processing networks neural networks processing q-bio.nc recognition robust type