The popularity of deep learning is due in part to its capabilities of handling large amounts of data and its efficiency when retraining the model has made it a useful tool when working on real-world data. Nowadays, these abilities are especially useful when trying to recognize patterns from inputs like images or videos, which present two dimensions of the big data world—volume and velocity.
Barbara Fusinska offers an overview of Microsoft Cognitive Toolbox, an open source framework offering various modules and algorithms enabling machines to learn like a human brain dedicated to solving deep learning challenges. It offers a set of built-in components and sophisticated algorithms, allows users to customize the machine-learning process, and enables easy integration with the Azure platform.
Barbara covers basic deep learning concepts and explains how to use Cognitive Toolkit when approaching them. By applying reinforcement learning and neural networks algorithms to several machine-learning challenges, Barbara demonstrates the capabilities of the platform. Along the way, she also covers use cases on using core components when building solutions and publishing them to the Azure cloud and previews the technical roadmap for the rest of 2017.
Barbara Fusinska is a machine learning engineer at Google. She has a strong software development background and is experienced in building diverse software systems. Barbara focuses on data science and big data and still enjoys programming as well. She believes in the importance of data and metrics when growing a successful business. Barbara is a frequent speaker at conferences.
©2017, O’Reilly UK Ltd • (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