no code implementations • 9 Nov 2023 • Kevin Miller, Ryan Murray
This work introduces Dirichlet Active Learning (DiAL), a Bayesian-inspired approach to the design of active learning algorithms.
1 code implementation • 19 Jul 2023 • James Chapman, Bohan Chen, Zheng Tan, Jeff Calder, Kevin Miller, Andrea L. Bertozzi
Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximally improving the underlying classifier's performance.
no code implementations • 17 Jun 2023 • Bohan Chen, Kevin Miller, Andrea L. Bertozzi, Jon Schwenk
We develop a graph active learning pipeline (GAP) to detect surface water and in-river sediment pixels in satellite images.
no code implementations • 13 Nov 2022 • Ted Moskovitz, Kevin Miller, Maneesh Sahani, Matthew M. Botvinick
We apply a single model based on this observation to findings from research on executive control, reward-based learning, and judgment and decision making, showing that seemingly diverse dual-process phenomena can be understood as domain-specific consequences of a single underlying set of computational principles.
1 code implementation • 27 Oct 2022 • Kevin Miller, Jeff Calder
We show that uncertainty sampling is sufficient to achieve exploration versus exploitation in graph-based active learning, as long as the measure of uncertainty properly aligns with the underlying model and the model properly reflects uncertainty in unexplored regions.
no code implementations • 15 Sep 2022 • Zeb Kurth-Nelson, Timothy Behrens, Greg Wayne, Kevin Miller, Lennart Luettgau, Ray Dolan, Yunzhe Liu, Philipp Schwartenbeck
Replay in the brain has been viewed as rehearsal, or, more recently, as sampling from a transition model.
1 code implementation • 31 Mar 2022 • Kevin Miller, John Mauro, Jason Setiadi, Xoaquin Baca, Zhan Shi, Jeff Calder, Andrea L. Bertozzi
We use a Convolutional Neural Network Variational Autoencoder (CNNVAE) to embed SAR data into a feature space, and then construct a similarity graph from the embedded data and apply graph-based semi-supervised learning techniques.
no code implementations • 12 Dec 2021 • Yifan Hua, Kevin Miller, Andrea L. Bertozzi, Chen Qian, Bao Wang
As such, our proposed overlay networks accelerate convergence, improve generalization, and enhance robustness to clients failures in DFL with theoretical guarantees.
2 code implementations • 14 Oct 2021 • Kevin Miller, Andrea L. Bertozzi
Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.
no code implementations • 25 Jul 2020 • Andrea L. Bertozzi, Bamdad Hosseini, Hao Li, Kevin Miller, Andrew M. Stuart
Graph-based semi-supervised regression (SSR) is the problem of estimating the value of a function on a weighted graph from its values (labels) on a small subset of the vertices.
no code implementations • 21 Jul 2020 • Kevin Miller, Hao Li, Andrea L. Bertozzi
We present a novel adaptation of active learning to graph-based semi-supervised learning (SSL) under non-Gaussian Bayesian models.
no code implementations • 8 May 2019 • Pedro A. Ortega, Jane. X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
2 code implementations • 20 May 2017 • Kevin Miller, Chris Hettinger, Jeffrey Humpherys, Tyler Jarvis, David Kartchner
We present a general framework called forward thinking for deep learning that generalizes the architectural flexibility and sophistication of deep neural networks while also allowing for (i) different types of learning functions in the network, other than neurons, and (ii) the ability to adaptively deepen the network as needed to improve results.