4 papers
Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning
Marissa Connor, Vincent Emanuele
Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such…
Generative causal explanations of black-box classifiers
Matthew O'Shaughnessy, Gregory Canal, Marissa Connor +2
We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in…
Variational Autoencoder with Learned Latent Structure
Marissa C. Connor, Gregory H. Canal, Christopher J. Rozell
The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this…
Representing Closed Transformation Paths in Encoded Network Latent Space
Marissa Connor, Christopher Rozell
Deep generative networks have been widely used for learning mappings from a low-dimensional latent space to a high-dimensional data space. In many cases, data transformations are d…