Deep learning is central to recent innovations in AI. If you don’t want to run your code in the cloud and prefer to build your own local rig optimized for TensorFlow and machine learning, then this post is for you.

One point to note is that TensorFlow has a slightly unusual computation scheme which might be particularly intimidating to novice programmers. The computations are built into a ‘computation graph’ which is then run all at once. So to add two variables, a and b, TensorFlow would first encode the ‘computation’ a+b into a computation graph. Before running this graph, trying to access this graph will not give a result – the result hasn’t been processed yet! Instead, it will give you the graph. Only after running the graph will you have access to the actual answer. Bear this in mind, as it will help clear confusions in your later explorations with TensorFlow.

Stephanie Hurlburt, Binomial co-founder, joins Scott Hanselman to talk about their current projects. Stephanie covers the differences between CPU and GPU, how Binomial balances open standards with its paid products, and where to get started with open source image/texture compression. From Scott, you’ll hear about open source in healthcare, including his personal experiences with diabetes technology, where to learn more, and ways to get involved.

You’ll leave with a few new projects to check out, and, whatever you’re passionate about, there’s likely an open source community or project waiting for you to join – or start.