Abstract: Variational Auto-Encoders (VAEs) are cutting edge deep learning technology. The purpose of a VAE is to decomplexify data. Another name for this task is dimension reduction. The idea is that you have data that has lots of variables in it, but with so many variables it’s hard to understand what’s going on. You want to think about your customers, not as this huge spreadsheet with hundreds or thousands of pieces of information about each customer, but as something simple. You want to think of just a couple of customer types, with the idea that you know people are not very different from those ideal types.
Once you have someone's type, you know almost everything you really need to know from that huge dataset. The type gives you a good summary of the data that you’ve been collecting about the customer, but thanks to the VAE it’s a simple description. For sure you’re going to lose some detail, but not much. And that simple description produced by the VAE is going to be super useful. Everyone in the business is going to be able to look at that type and immediately know the story of the customer. Instant insight.
Bio: Yaniv Ben-Ami loves seeing data with my own eyes. It’s frustrating to him that it’s impossible to observe the geometry of multidimensional data that’s more than 3d. Yaniv first became obsessed with this challenge as a Bioinformatics undergrad at Tel Aviv University. Little did Yaniv knows that my obsession would become an epic journey. As an Economics Master student, Yaniv met the ultimate beast of a data set. This beast is The American Time Use Survey (ATUS), which has 389 dimensions. To Yaniv, it appeared as a 389-head Hydra that nobody would dare to slay. Gazing upon that beast, Yaniv initially fell into despair. Fast forward 15 years, 3 kids and a Ph.D. in Economics from Yale, Yaniv reads Deep Learning in Python by François Chollet. Within this tome of wisdom, Yaniv found a gift from the Gods. A deep learning algorithm by the name of Variational Auto-Encoder. This mythical weapon can map multidimensional data to a one-dimensional range and maintain relative distances. Finally, Yaniv Ben-Ami can see the whole data set. Yaniv will show you how he used this weapon to slay the ATUS monster. Just in case there’s a monster you want to slay.