The Most Unresolved Problem In Machine Learning

These questions originally appeared on Quora – the knowledge sharing network where compelling questions are answered by people with unique insights. Answers by Kevin Murphy, Research Scientist at Google, former Professor at UBC, on Quora. Q: What is the most important unresolved problem in machine learning? A: Unsupervised learning. In particular, what objective function should we use? Maximizing likelihood of the observed data, or even of future observed data, seems like the wrong thing to aim for. Consider, for example, predicting every pixel in the next N frames of video. Do we care about the exact intensity values? No, we care about predicting what the world is going to do next (will the car turn left or right? will the glass break if I drop it?). Somehow humans and animals…


Link to Full Article: The Most Unresolved Problem In Machine Learning