We use coupled hidden Markov models to automatically annotate the 371 Bach chorales in the Riemenschneider edition, a corpus containing approximately 100,000 notes and 20,000 chords. We give three separate analyses that achieve progressively greater accuracy at the cost of making increasingly strong assumptions about musical syntax. Although our method makes almost no use of human input, we are able to identify both chords and keys with an accuracy of 85% or greater when compared to an expert human analysis, resulting in annotations accurate enough to be used for a range of music-theoretical purposes, while also being free of subjective human judgments. Our work bears on longstanding debates about the objective reality of the structures postulated by standard Western harmonic theory, as well as on specific questions about the nature of Western harmonic syntax.

Outlines how augmented analytics changes the way security, operations and risk professionals navigate or prevent potential risks before they happen. Seerist Inc., the leading augmented analytics solution for threat and security professionals, today announced the availability of its white paper, Turning Infinite Data into Insightful Threat and Risk Strategies. This white paper was written to demonstrate how leaders can better leverage global data to make more informed, strategic decisions by combining the power of machine learning, human analysis, and natural language capabilities. "Data continues to grow at an accelerated rate every year with 89 percent of big data created in the last two years. It is simply impossible for humans to adequately access and evaluate the vast quantum of information available, yet the value it provides can be life changing and should not be ignored," said Jim Brooks, Seerist's CEO.

The typical approach to combating fraud is to look at all the different ways fraudsters operate and find some indicator based on their objectives. But every time one fraud tactic is identified, the fraudster evolves its tactics to evade detection. Increasingly, fraud resembles valid traffic. This article originally appeared on the TrafficGuard blog. Every time the fraudster finds a new vulnerability, valuable time is lost in defining the tactic and finding the rule to stop it.

What are the most cutting-edge applications of AI for B2B market research? How much busywork can analysts delegate to a bot? Will automated systems replace the need for human analysis? We (virtually) sent our analysts to the 2017 QRCA Mini-Conference on Artificial Intelligence to find out. Here are their key takeaways.

Marketers who want to up their social media game are watching the evolution of image analysis intently. The potential value is clear, but the "how" has been less so. Think about all of the data and images that are stored within image-friendly platforms like Instagram and Snapchat. There are more than 3 billion such images shared on social media every day. To better understand their audiences, marketers need to know how artificial intelligence and machine learning can help them analyze social media images that feature their brands (or their competitors' brands) to see how consumers are using products and better market to those audiences.