Teaching Neural Networks a Sense of Geometry
By taking neural networks back to the school bench and teaching them some elements of geometry and topology, we can build algorithms that can reason about the shape of data. Surprisingly these methods can be useful not only for computer vision but in a wide range of applications, such as evaluating and improving the learning of embeddings or the distribution of samples originating from generative models. This is the promise of the emerging field of Topological Data Analysis (TDA) which we will introduce and review recent works at its intersection with machine learning.
While working as a data scientist at Ericsson, Jens is also pursuing a PhD in machine learning at KTH within the WASP program. He believes that teaching computers a sense of geometrical recognition and reasoning is a promising direction if we want to develop more powerful AIs. One way to do so is to expand the mathematical toolkit underlying machine learning to include math from less well-known fields such as computational geometry and topology. Jens will discuss some of the results and challenges in doing so.
