Deep learning is a significant sub-field of machine learning and a branch of artificial intelligence. The way in which deep learning works is by inferring high-level abstractions from raw data by using a deep graph with many layers of processing.
Deep learning structures, for example, Convolutional deep Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) have been connected to computer vision, speech recognition, natural language processing, and audio recognition to deliver results.
The Rekognition service employs deep learning in order to provide its various features behind the scenes. It uses pre-trained models so that users do not have to train the system. The exact details are proprietary and confidential to Amazon, but we can see how it works and how to use Rekognition in this chapter.