6 citations · 11 across the 8 of their papers we have counts for
9 papers
Reproducing Kernel Hilbert Space Pruning for Sparse Hyperspectral Abundance Prediction
Michael G. Rawson, Timothy Doster
Hyperspectral measurements from long range sensors can give a detailed picture of the items, materials, and chemicals in a scene but analysis can be difficult, slow, and expensive…
How many dimensions are required to find an adversarial example?
Charles Godfrey, Henry Kvinge, Elise Bishoff +4
Past work exploring adversarial vulnerability have focused on situations where an adversary can perturb all dimensions of model input. On the other hand, a range of recent works co…
In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?
Henry Kvinge, Tegan H. Emerson, Grayson Jorgenson +3
It is often said that a deep learning model is "invariant" to some specific type of transformation. However, what is meant by this statement strongly depends on the context in whic…
DNA: Dynamic Network Augmentation
Scott Mahan, Tim Doster, Henry Kvinge
In many classification problems, we want a classifier that is robust to a range of non-semantic transformations. For example, a human can identify a dog in a picture regardless of…
Reward-Free Attacks in Multi-Agent Reinforcement Learning
Ted Fujimoto, Timothy Doster, Adam Attarian +2
We investigate how effective an attacker can be when it only learns from its victim's actions, without access to the victim's reward. In this work, we are motivated by the scenario…
Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
Scott Mahan, Henry Kvinge, Tim Doster
Building invariance to non-meaningful transformations is essential to building efficient and generalizable machine learning models. In practice, the most common way to learn invari…
Argumentative Topology: Finding Loop(holes) in Logic
Sarah Tymochko, Zachary New, Lucius Bynum +4
Advances in natural language processing have resulted in increased capabilities with respect to multiple tasks. One of the possible causes of the observed performance gains is the…
An optimal transport model for imaging in atmospheric turbulence
Jonathan M. Nichols, Abbie T. Watnik, Timothy Doster +4
We describe a new model for image propagation through open air in the presence of changes in the index of refraction (e.g. due to turbulence) using the theory of optimal transport.…
Gradual DropIn of Layers to Train Very Deep Neural Networks
Leslie N. Smith, Emily M. Hand, Timothy Doster
We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a trainable shallow network and newly added l…