16.6 Convolutional Neural Networks for Vision; Multi-Classification with the MNIST Dataset
In the “Machine Learning” chapter, we classified handwritten digits using the 8-by-8-pixel, low-resolution images from the Digits dataset bundled with Scikit-learn. That dataset is based on a subset of the higher-resolution MNIST handwritten digits dataset. Here, we’ll use MNIST to explore deep learning with a convolutional neural network35 (also called a convnet or CNN). Convnets are common in computer-vision applications, such as recognizing handwritten digits and characters, and recognizing objects in images and video. They’re also used in non-vision applications, such as natural-language processing and recommender systems.
Get Intro to Python for Computer Science and Data Science: Learning to Program with AI, Big Data and The Cloud now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
