no code implementations • 2 Dec 2021 • Ted Fujimoto, Timothy Doster, Adam Attarian, Jill Brandenberger, Nathan Hodas
We investigate how effective an attacker can be when it only learns from its victim's actions, without access to the victim's reward.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 8 Apr 2021 • Elliott Skomski, Aaron Tuor, Andrew Avila, Lauren Phillips, Zachary New, Henry Kvinge, Courtney D. Corley, Nathan Hodas
Recently proposed few-shot image classification methods have generally focused on use cases where the objects to be classified are the central subject of images.
no code implementations • 15 Nov 2019 • Lawrence Phillips, Garrett Goh, Nathan Hodas
Neural network interpretability is a vital component for applications across a wide variety of domains.
no code implementations • 14 Sep 2019 • Chris Careaga, Brian Hutchinson, Nathan Hodas, Lawrence Phillips
In this work, we address the task of few-shot video action recognition with a set of two-stream models.
no code implementations • 22 Aug 2017 • Enoch Yeung, Soumya Kundu, Nathan Hodas
The Koopman operator has recently garnered much attention for its value in dynamical systems analysis and data-driven model discovery.
no code implementations • WS 2017 • Lawrence Phillips, Kyle Shaffer, Dustin Arendt, Nathan Hodas, Svitlana Volkova
Language in social media is a dynamic system, constantly evolving and adapting, with words and concepts rapidly emerging, disappearing, and changing their meaning.
no code implementations • ACL 2017 • Svitlana Volkova, Kyle Shaffer, Jin Yea Jang, Nathan Hodas
In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news {--} satire, hoaxes, clickbait and propaganda.
no code implementations • 6 Jun 2017 • Lawrence Phillips, Nathan Hodas
Increasingly, cognitive scientists have demonstrated interest in applying tools from deep learning.