Historical Thoughts on Modern Prediction

Ben Recht
Professor, UC Berkeley
Abstract
I’ll tell a history of statistical prediction, beginning with Wiener and Rosenblatt and ending with contemporary machine learning. This history will highlight the cyclical rediscovery of pattern recognition and subsequent disillusionment with its shortcomings. I will describe how much of our theoretical understanding of statistical learning has not deepened for over half a century. I will trace how the empirical standards of the field arose from technological and social developments, many of which transpired in Palo Alto in the 1960s. And I will ask for leads on some hard to find datasets that may lie in dusty archives at Stanford or SRI.
Most of the material for this talk will be drawn from a new graduate textbook, “Patterns, Predictions, and Action: A Story About Machine Learning,” co-authored with Moritz Hardt.
Bio
Benjamin Recht is a Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley.

[@EricSiegelPredicts]

Well done!! I’ve never before seen the inside of what has always to me felt only like a general sense of primordial emergence of the fundamental ML concepts.