Oct 13, 2020

New deep learning models: Fewer neurons, more intelligence

Posted by in categories: robotics/AI, transportation

Artificial intelligence has arrived in our everyday lives—from search engines to self-driving cars. This has to do with the enormous computing power that has become available in recent years. But new results from AI research now show that simpler, smaller neural networks can be used to solve certain tasks even better, more efficiently, and more reliably than ever before.

An international research team from TU Wien (Vienna), IST Austria and MIT (USA) has developed a new system based on the brains of tiny animals, such as threadworms. This novel AI-system can control a vehicle with just a few artificial neurons. The team says that system has decisive advantages over previous models: It copes much better with noisy input, and, because of its simplicity, its mode of operation can be explained in detail. It does not have to be regarded as a complex “black box”, but it can be understood by humans. This new deep learning model has now been published in the journal Nature Machine Intelligence.

Comments are closed.