We identify some well-known software verification problems, using real-world examples from open-source projects and see how we might apply some deep learning principles to address them.  In the various points where we may test the Java runtime, we find candidates for deep learning.  What is required?  We need a problem to solve, a model that describes it, and a large amount of data to feed the neural network.

We will step through a simple example of where and how to apply deep learning to more effectively test Java runtimes.  By covering the basics of deep learning and the simple example, the intent of this presentation is to spark curiosity and generate ideas on future applications of this machine learning approach to problem-solving.

Anybody in a technical or non-technical role interested in using deep learning to test Java runtimes.

Shelley Lambert, J9 Software Developer in Ottawa, Canada https://twitter.com/shelleymlambert

Dave Nugent, IBM Developer Advocate in San Francisco https://twitter.com/drnugent

Learning about Deep Learning: Applications for OpenJDK/Java Verification