AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making

no code implementations • 7 Dec 2023 • Shusen Liu, Haichao Miao, Zhimin Li, Matthew Olson, Valerio Pascucci, Peer-Timo Bremer

With recent advances in multi-modal foundation models, the previously text-only large language models (LLM) have evolved to incorporate visual input, opening up unprecedented opportunities for various applications in visualization.

Decision Making

Modern Neural Networks Generalize on Small Data Sets

no code implementations • NeurIPS 2018 • Matthew Olson, Abraham Wyner, Richard Berk

In this paper, we use a linear program to empirically decompose fitted neural networks into ensembles of low-bias sub-networks.

General Classification Small Data Image Classification

Open Set Learning with Counterfactual Images

no code implementations • ECCV 2018 • Lawrence Neal, Matthew Olson, Xiaoli Fern, Weng-Keen Wong, Fuxin Li

In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training.

Classification counterfactual +4

Explaining the Success of AdaBoost and Random Forests as Interpolating Classifiers

no code implementations • 28 Apr 2015 • Abraham J. Wyner, Matthew Olson, Justin Bleich, David Mease

We introduce a novel perspective on AdaBoost and random forests that proposes that the two algorithms work for similar reasons.