An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution Uber uses convolutional neural networks in many domains that could potentially involve coordinate transforms, from designing self-driving vehicles to automating street sign detection to build maps and maximizing the efficiency of spatial movements in the Uber Marketplace. In deep learning, few ideas have experienced
![An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://cdn-ak-scissors.b.st-hatena.com/image/square/9087d1dc98f57683dd05eaf7a4d3285b03d0996b/height=288;version=1;width=512/https%3A%2F%2Fblogapi.uber.com%2Fwp-content%2Fuploads%2F2018%2F07%2FFacebook-1.png)