Many of the deep- earning algorithms used in AI applications are powered by large matrix operations. TensorFlow provides data flow graphs for such operations, allowing algorithms to be easily parallelized across multiple processors or machines. This makes TensorFlow an ideal environment for implementing neural networks and other deep-learning algorithms. Dylan Bargteil offers an overview of the TensorFlow graph using its Python API. You’ll start with simple machine learning algorithms and move on to implementing neural networks, including convolutional neural networks to provide object recognition for machine vision, recurrent neural networks, including long short-term memory architectures, that allow the comprehension of time series and language, and generative networks, which give AI applications the ability to create output. Along the way, Dylan covers several real-world deep learning applications, including machine vision, text processing, and generative networks.
Dylan Bargteil is a data scientist in residence at the Data Incubator, where he works on research-guided curriculum development and instruction. Previously, he worked with deep learning models to assist surgical robots and was a research and teaching assistant at the University of Maryland, where he developed a new introductory physics curriculum and pedagogy in partnership with the Howard Hughes Medical Institute (HHMI). Dylan studied physics and math at the University of Maryland and holds a PhD in physics from New York University.
©2018, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org