no code implementations • 22 Mar 2024 • John Fischer, Marko Orescanin, Justin Loomis, Patrick McClure
Aggregation strategies have been developed to pool or fuse the weights and biases of distributed deterministic models; however, modern deterministic deep learning (DL) models are often poorly calibrated and lack the ability to communicate a measure of epistemic uncertainty in prediction, which is desirable for remote sensing platforms and safety-critical applications.
no code implementations • 6 Feb 2023 • Edgar W. Jatho, Logan O. Mailloux, Eugene D. Williams, Patrick McClure, Joshua A. Kroll
Many stakeholders struggle to make reliances on ML-driven systems due to the risk of harm these systems may cause.
1 code implementation • 2 May 2022 • Lukas Muttenthaler, Charles Y. Zheng, Patrick McClure, Robert A. Vandermeulen, Martin N. Hebart, Francisco Pereira
This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task.
1 code implementation • 8 Sep 2020 • Patrick McClure, Gabrielle Reimann, Michal Ramot, Francisco Pereira
This short article describes a deep neural network trained to perform automatic segmentation of human body parts in natural scenes.
1 code implementation • 23 Apr 2020 • Patrick McClure, Dustin Moraczewski, Ka Chun Lam, Adam Thomas, Francisco Pereira
We introduce two quantitative evaluation procedures for saliency map methods in fMRI, applicable whenever a DNN or linear model is being trained to decode some information from imaging data.
1 code implementation • 3 Dec 2018 • Patrick McClure, Nao Rho, John A. Lee, Jakub R. Kaczmarzyk, Charles Zheng, Satrajit S. Ghosh, Dylan Nielson, Adam G. Thomas, Peter Bandettini, Francisco Pereira
In this paper, we describe a Bayesian deep neural network (DNN) for predicting FreeSurfer segmentations of structural MRI volumes, in minutes rather than hours.
no code implementations • NeurIPS 2018 • Patrick McClure, Charles Y. Zheng, Jakub R. Kaczmarzyk, John A. Lee, Satrajit S. Ghosh, Dylan Nielson, Peter Bandettini, Francisco Pereira
Collecting the large datasets needed to train deep neural networks can be very difficult, particularly for the many applications for which sharing and pooling data is complicated by practical, ethical, or legal concerns.
no code implementations • 5 Nov 2016 • Patrick McClure, Nikolaus Kriegeskorte
We tested the calibration of the probabilistic predictions of Bayesian convolutional neural networks (CNNs) on MNIST and CIFAR-10.
no code implementations • 12 Nov 2015 • Patrick McClure, Nikolaus Kriegeskorte
We propose representational distance learning (RDL), a stochastic gradient descent method that drives the RDMs of the student to approximate the RDMs of the teacher.