MIT, TU Wien & IST Austria Brain-Based AI Self-Drives With Just a Few Neurons

Modern AI has produced models that exceed human performance across countless tasks. Now, an international research team is suggesting AI might become even more efficient and reliable if it learns to think more like worms. In a paper recently published in Nature Machine Intelligence journal, the team from MIT CSAIL, TU Wien in Vienna, and IST Austria proposes an AI system that mimics biological models. The system was developed based on the brains of tiny animals such as threadworms and is able to control a vehicle using just a small number of artificial neurons. The researchers say the system has decisive advantages over other deep learning models because it copes much better with noisy input, and, because of its simplicity, its operations can be explained in detail -- alleviating the "black box" concerns affecting today's deep AI models. Explains TU Wien Cyber-Physical Systems head Professor Radu Grosu in a project press release: "For years, we have been investigating what we can learn from nature to improve deep learning.