/ Oliver Morsch
What a folding ruler can tell us about neural networks
Researchers at the University of Basel have developed mechanical models that can predict how effectively the different layers of a deep neural network transform data. Their results improve our understanding of these complex systems and suggest better strategies for training neural networks.
Deep neural networks are at the heart of artificial intelligence, ranging from pattern recognition to large language and reasoning models like ChatGPT. The principle: during a training phase, the parameters of the network’s artificial neurons are optimized in such a way that they can carry out specific tasks, such as autonomously discovering objects or characteristic features in images.
You may find the full article in the UNI NEWS.