Add to Favourites
To login click here
AI has the potential to revolutionize many aspects of our lives, from electric vehicles to medical care. To make this a reality, scientists and engineers are using a technique called ‘physics-informed neural networks’ or ‘scientific machine learning’ which gives AI a starting point based on existing knowledge about a system. This approach helps limit the number of solutions an AI has to experiment with, and can be used to teach robots how to walk, for example. The idea that AI works best when the problem is as narrowly defined as possible is a core concept of this approach.