Deep learning has had many successes in supervised learning but generally depends on labeled data. However, deep learning has also been applied to RBMs and unsupervised pretraining, particularly for use cases such as image search and better object recognition. Eventually RBMs have been succeeded by variational autoencoders and various kinds of GANs (generative adverserial networks).
Adam Gibson demonstrates how to use variational autoencoders to automatically label time series location data. You’ll explore the challenge of imbalanced classes and anomaly detection, learn how to leverage deep learning for automatically labeling (and the pitfalls of this), and discover how you can deploy these techniques in your organization.
Adam Gibson is the CTO and cofounder of Skymind, a deep learning startup focused on enterprise solutions in banking and telco, and the coauthor of Deep Learning: A Practitioner’s Approach.
©2017, 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. • email@example.com