2 citations · 4 across the 2 of their papers we have counts for
3 papers
Unifying AI Algorithms with Probabilistic Programming using Implicitly Defined Representations
Avi Pfeffer, Michael Harradon, Joseph Campolongo +1
We introduce Scruff, a new framework for developing AI systems using probabilistic programming. Scruff enables a variety of representations to be included, such as code with stocha…
Explainable Artificial Intelligence (XAI) for Increasing User Trust in Deep Reinforcement Learning Driven Autonomous Systems
Jeff Druce, Michael Harradon, James Tittle
We consider the problem of providing users of deep Reinforcement Learning (RL) based systems with a better understanding of when their output can be trusted. We offer an explainabl…
Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations
Michael Harradon, Jeff Druce, Brian Ruttenberg
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions…