Spencer Greenberg holds a B.S. Magna Cum Laude in Applied Mathematics & Computer Science, from Columbia University, and a Ph D. in Machine Learning, from NYU. Prior to Rebellion Research, he was Software Developer, Neuberger Berman, LLC and Engineer in The Investigative Project for Terrorism. Spencer has been interviewed  on CNBC, Bloomberg News, Canada’s BNN, and in the Wall Street Journal. He has also lectured at Columbia School of Business, and the NYU Stern School of Business.

Q. What type of machine learning do you use for Rebellion Research’s AI system?

A. We apply our own proprietary machine learning approach, which performs a form of Bayesian probabilistic modeling. We have found that off the shelf machine learning solutions usually do not work very well in our problem domain.

Q. When did you become interested in machine learning and why did you get interested in machine learning?

A. I first became interested in machine learning outside of an academic context, and began to study it intensively on my own. It quickly dawned on me how incredibly powerful machine learning techniques are, and how important they will be as technology continues to advance. I decided to pursue graduate studies in machine learning to improve my knowledge rapidly.

Q. What leads you to believe AI is the way of the future?

A. Machine learning addresses the question of how to make accurate predictions from data by having a computer automatically learn from examples. The range of applications that this paradigm applies to is tremendous, from face recognition, to game playing, to product recommendation, to language translation to stock trading.

Q. Where can we expect to see machine learning in society in the near future?

A. Machine learning has many very interesting future applications: 

• Use in self-driving cars, such as in Google’s current driverless car project
• Increased usage for emotion detection from facial images, to allow computers to track and respond to how we feel
• Applications for real time object recognition, as is necessary for many augmented reality applications
• Improving language translation systems
• Learning to map brain imaging data to an indicator of what a person is thinking about
• Enhancing the automated identification of pre-cursors to serious ailments, such a cancer

Q. Is there a specific type of machine learning you are excited about?

A. There are exciting developments in machine learning applied to extremely large data sets, sizes not tractable with classic machine learning methods. Additionally, deep learning methods, which automatically extract important features from data as they learn to make predictions, have been seeing considerable advances.

Q. What stage in the machine learning technological birth would you say we are in today in 2014?

A. It's tough to say, but it's clear that decades of fruitful research into machine learning lie ahead, and hundreds of further applications.

Q. What would you say is our biggest benefit from machine learning and AI so far?

A. It is not so much that machine learning has a single killer application that has radically changed our lives. Rather, machine learning has become integrated into hundreds of different applications. Often we are not even aware of it being there, even as it helps us. For instance, Netflix uses machine learning to improve its movie recommendations for us, Amazon applies it to recommending better products, Google uses it to translate languages, and digital cameras relies on it to identify faces in photographs. We're using the output of machine learning algorithms all the time, we just don't realize it.