In this episode of the AI show Erika explains how to create deep learning models with music as the input. She begins by describing the problem of generating music by specifically describing how she generated the appropriate features from a midi file. She then describes the deep learning model she used in order to generate music.

Learn more:

Deep learning and AI are fundamentally changing the way data is used in computation. They enable computing capabilities that will transform almost every industry, scientific domain, and public usage of data and compute.

The recent success of deep learning algorithms can be seen as the culmination of decades of progress in three areas: research in DL algorithms, broad availability of big data infrastructure, and the massive growth of computation power produced by Moore’s law and the advent of parallel compute architectures.

Deep learning has been employed successfully in such diverse areas as healthcare, transportation, industrial IoT, finance, entertainment, and retail, in addition to high-performance computing.

Examples shown in this video illustrate how the approach works and how it complements high-performance data analytics and traditional business intelligence.

In my previous post, I featured a video on Microsoft Cognitive Toolkit (CNTK). If you’ve not heard of it, CNTK is a production-grade, open-source, deep-learning library. It’s the toolkit behind a Microsoft’s many AI initiatives.

CNTK embraces fully open development, is available on GitHub, and provides support for both Windows and Linux. The latest release packs in several enhancements: most notably Python/C++ API support, easy-to-onboard tutorials (as Python notebooks) and examples, and an easy-to-use Layers interface.

These enhancements, combined with unparalleled scalability on NVIDIA hardware, were demonstrated by both NVIDIA at SuperComputing 2016 and Cray at NIPS 2016.

These enhancements from the CNTK supported Microsoft in its recent breakthrough in speech recognition, reaching human parity in conversational speech.

The toolkit is used in all kinds of deep learning, including image, video, speech, and text data. The speakers will discuss the current features of the toolkit’s release and its application to deep learning projects.