Search Results for author:
Found 7 papers, 3 papers with code
Self-Play Learning Without a Reward Metric
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 function for game outcomes, requiring the users of the algorithm to explicitly balance different components of the reward against each other, such as the game winner and margin of victory.
Noisier2Noise: Learning to Denoise from Unpaired Noisy Data
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.
Reconstructing Network Inputs with Additive Perturbation Signatures
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 model outputs and the ability evaluate the model on additive perturbations to the input.
Coevolutionary Neural Population Models
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 neural networks engage in coevolutionary interactions.
Protecting JPEG Images Against Adversarial Attacks
As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed.
Deflecting Adversarial Attacks with Pixel Deflection
Despite their robustness to natural variations, image pixel values can be manipulated, via small, carefully crafted, imperceptible perturbations, to cause a model to misclassify images.
Semantic Perceptual Image Compression using Deep Convolution Networks
Here, we present a powerful cnn tailored to the specific task of semantic image understanding to achieve higher visual quality in lossy compression.
