Practical Automated Machine Learning on Azure

Foreword

I vividly remember my first undergraduate class in artificial intelligence (AI). My father had worked for years on “expert systems,” and I was at MIT to learn from the best how to perform this wizardry. Marvin Minsky, one of the founders of the field, even taught a series of guest lectures there. It was about midway through the semester when the great disillusionment hit me: “It’s all just a bunch of tricks!” There was no “intelligence” to be found; just a bunch of brittle rules engines and clever use of math. This was in the early ’90s and the start of my own personal AI winter, when I dismissed AI as not having much use.

Years later, while I was working on advertising systems, I finally saw that there was power in this “bunch of tricks.” Algorithms that had been hand-tuned for months by talented engineers were being beaten by simple models provided with lots of data. I saw that the explosion that was to come simply needed more data and more computation to be effective. Over the past 5 to 10 years, the explosion in both big data and computation power has unleashed an industry that has had lots of starts and stops to it.

This time is different. While the hype about AI is still tremendously high, the potential applications of practical AI have really just begun to hit the business world. The rules or people making predictions today will be replaced virtually every place by AI algorithms. The value AI creates for businesses is tremendous, from being better able to value ...