Location:Training / Machine Learning/Algorithm / Deep Learning and Computer Vision Stanford Li Feifei / Policy gradient, hard attention

Computer vision has become ubiquitous in our society with applications in search, image recognition, apps, imaging, medicine, drones, and self-driving cars. Many of these applications, such as: image classification, localization and detection, are completed by visual recognition technology. Newly discovered neural network methods (also known as "deep learning") have greatly improved the advanced performance of visual recognition systems.