4 papers
Self-Play Learning Without a Reward Metric
Dan Schmidt, Nick Moran, Jonathan S. Rosenfeld +2
The AlphaZero algorithm for the learning of strategy games via self-play, which has produced superhuman ability in the games of Go, chess, and shogi, uses a quantitative reward fun…
Noisier2Noise: Learning to Denoise from Unpaired Noisy Data
Nick Moran, Dan Schmidt, Yu Zhong +1
We present a method for training a neural network to perform image denoising without access to clean training examples or access to paired noisy training examples. Our method requi…
Monotone Learning with Rectified Wire Networks
Veit Elser, Dan Schmidt, Jonathan Yedidia
We introduce a new neural network model, together with a tractable and monotone online learning algorithm. Our model describes feed-forward networks for classification, with one ou…
Proactive Message Passing on Memory Factor Networks
Patrick Eschenfeldt, Dan Schmidt, Stark Draper +1
We introduce a new type of graphical model that we call a "memory factor network" (MFN). We show how to use MFNs to model the structure inherent in many types of data sets. We also…