Microsoft researchers are publicly releasing Microsoft Vision Model ResNet-50, a pretrained vision model that sets state of the art by mean average score across 7 computer vision benchmarks. Learn how multi-task learning and web supervision make it possible: aka.ms/AAb0mih | Microsoft Research

Automate user interfaces using agents that interact with websites and desktop apps, powered by AI vision and understanding. Read more: http://msft.it/6186S97qw | Microsoft

Microsoft Vision Model ResNet-50 is a state-of-the-art pretrained vision model that uses multi-task learning and web supervision for high performance with lower cost in production settings. In our webinar, learn to use the model to build an image classifier: https://aka.ms/AAb5uto | Microsoft Research