Michael Mozer, Scientific Advisor at AnswerOn and Professor at the University of Colorado discusses AnswerOn’s early days of churn prediction.
Although neural networks have been around for sixty years, a seminal research paper appeared thirty years ago that revolutionized the field. The paper was called Learning representations by back-propagating errors (Rumelhart, Hinton, & Williams, 1986). In this post, I’ll explain what “learning representations” means and why this idea is so central to neural networks.
Michael Mozer, Scientific Advisor at AnswerOn and Professor at the University of Colorado discusses the rise and fall, and rise again of neural networks. This post considers how we owe today’s neural networks to those from the 1980s.