Locomotion modeling evolves with brain-inspired neural networks - EPFL

A team of scientists at EPFL have built a new neural network system that can help understand how animals adapt their movement to changes in their own body and to create more powerful artificial intelligence systems. Deep learning has been fueled by artificial neural networks, which stack simple computational elements on top of each other, to create powerful learning systems. Given enough data, these systems can solve challenging tasks like recognize objects, beat human's at Go and also control robots. "As you can imagine, the architecture of how you stack these elements on top of each other might influence how much data you need to learn and what the ceiling performance is," says Professor Alexander Mathis at EPFL's School of Life Sciences. Working with doctoral students Alberto Chiappa and Alessandro Marin Vargas, the three scientists have developed a new network architecture called DMAP for "Distributed Morphological Attention Policy".