317 citations · 381 across the 14 of their papers we have counts for
16 papers
Learn to explain yourself, when you can: Equipping Concept Bottleneck Models with the ability to abstain on their concept predictions
Joshua Lockhart, Daniele Magazzeni, Manuela Veloso
The Concept Bottleneck Models (CBMs) of Koh et al. [2020] provide a means to ensure that a neural network based classifier bases its predictions solely on human understandable conc…
Towards learning to explain with concept bottleneck models: mitigating information leakage
Joshua Lockhart, Nicolas Marchesotti, Daniele Magazzeni +1
Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predi…
Feature Importance for Time Series Data: Improving KernelSHAP
Mattia Villani, Joshua Lockhart, Daniele Magazzeni
Feature importance techniques have enjoyed widespread attention in the explainable AI literature as a means of determining how trained machine learning models make their prediction…
Reductive MDPs: A Perspective Beyond Temporal Horizons
Thomas Spooner, Rui Silva, Joshua Lockhart +2
Solving general Markov decision processes (MDPs) is a computationally hard problem. Solving finite-horizon MDPs, on the other hand, is highly tractable with well known polynomial-t…
Equivalent Laplacian and Adjacency Quantum Walks on Irregular Graphs
Thomas G. Wong, Joshua Lockhart
The continuous-time quantum walk is a particle evolving by Schrödinger's equation in discrete space. Encoding the space as a graph of vertices and edges, the Hamiltonian is proport…
Some people aren't worth listening to: periodically retraining classifiers with feedback from a team of end users
Joshua Lockhart, Samuel Assefa, Tucker Balch +1
Document classification is ubiquitous in a business setting, but often the end users of a classifier are engaged in an ongoing feedback-retrain loop with the team that maintain it.…