Semisupervised machine learning, the next frontier in AI
Who is this presentation for?
- CTOs, chief data analytics officers, CIOs, data scientists, and machine learning enthusiasts
Current deep learning approaches require large amounts of labeled data. The creation of labeled data is expensive, error prone, and time consuming. Despite these challenges, in the last decades tremendous successes in machine learning have been achieved in the area of supervised learning that requires the compilation of large datasets with labels (for example, grouping pictures based on the person in the image). In contrast, unsupervised learning algorithms do not require labels and require minimal human participation. However, due to significant technical difficulties, they haven’t been as successful as supervised learning algorithms.
Vinay Rao and Santi Adavani walk you through a new method to overcome the technical difficulties of self-supervised learning to extract value from very large unlabeled datasets using machine learning with minimal human intervention in cybersecurity, precision medicine, and predictive maintenance applications. The new method circumvents these difficulties and clears the way to scaling unsupervised learning algorithms to large and complex datasets. They demonstrate the method on a complex dataset through the choice of the correct comparison function between the objects of the dataset and the fully automatic algorithm and algorithm parameter selection.
- General knowledge of deep learning and supervised learning
What you'll learn
- Learn methods, tips, and tricks to achieve reasonable accuracies with minimal label data
Vinay Rao is the cofounder and CEO of RocketML, a machine learning platform on a mission to lead and enable transformation of the world toward artificial intelligence. RocketML implements bleeding-edge learning algorithms to perform at scale, delivering “near-real-time” training performance on any data size.
Santi Adavani is a cofounder at RocketML, where he and his team are building a superfast engine for building machine learning models. Previously, Santi was a product manager and software development lead in the Technology and Manufacturing Group at Intel. He holds a PhD in computational sciences from the University of Pennsylvania. His areas of expertise include high-performance computing, nonlinear optimization, partial differential equations, machine learning, and big data.
Diversity and Inclusion Sponsor
Premier Exhibitor Plus
R & D and Innovation Track Sponsor
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
For media/analyst press inquires