EurekAlert September 2, 2019
Before the neural network can begin to perform facial recognition, it is typically necessary to present it with thousands of faces. Much of these machines have been increasingly successful at pattern recognition but what goes on inside them as they learn their task is unknown. An international team of researchers (Portugal, Italy) has shown that artificial vision machines can learn to recognize complex images faster by using topological data analysis which was developed 25 years ago. Current neural networks are not good at topology. The team mathematically describe how to enforce certain symmetries, and this provides a strategy to build machine learning agents that can learn salient features from a few examples, by taking advantage of the knowledge injected as constraints…read more. TECHNICAL ARTICLE
The new approach allows artificial intelligence to learn to recognize transformed images much faster. Credit: Diogo Matias