5 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…
Reconstructing Network Inputs with Additive Perturbation Signatures
Nick Moran, Chiraag Juvekar
In this work, we present preliminary results demonstrating the ability to recover a significant amount of information about secret model inputs given only very limited access to mo…
Coevolutionary Neural Population Models
Nick Moran, Jordan Pollack
We present a method for using neural networks to model evolutionary population dynamics, and draw parallels to recent deep learning advancements in which adversarially-trained neur…
Protecting JPEG Images Against Adversarial Attacks
Aaditya Prakash, Nick Moran, Solomon Garber +2
As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed. These adversarial attacks make imperceptible…