Deep learning is an emerging field with the potential to transform whole industries, and to significantly affect software development.
This talk is an introduction to deep learning for Scala developers. We?ll see why deep learning enables a new programming paradigm, and how it?s related to functional programming.
We'll discuss what makes Scala an interesting choice for deep learning, and look at the current landscape of deep learning libraries for Scala. Equipped with that knowledge, we'll walk through a concrete example that shows you how to create, train and deploy a neural network using Scala.
No prior knowledge of deep learning, machine learning, or data science in general is assumed. Basic Scala experience will be helpful for understanding the example.
After listening to this talk, you should have a high-level understanding of how neural networks work, which problems they can help you to solve, and what their limitations are. You will know which Scala deep learning libraries are available. You should be prepared, and hopefully also be motivated to start your own deep learning experiments in Scala.
Sören Brunk is a research software engineer at the Institute of Ubiquitous Mobility Systems (IUMS). He has worked on machine learning projects since 2011, and has 4 years of Scala experience. Currently, he's using Scala and deep learning to optimize public transport utilization, and to detect dangerous traffic situations. He recently started writing about his Scala deep learning experiences on his blog.