no code implementations • 12 Apr 2023 • Daniel Golovin, Gabor Bartok, Eric Chen, Emily Donahue, Tzu-Kuo Huang, Efi Kokiopoulou, Ruoyan Qin, Nikhil Sarda, Justin Sybrandt, Vincent Tjeng
We are living in a golden age of machine learning.
1 code implementation • 20 Jun 2019 • Fang-Chieh Chou, Tsung-Han Lin, Henggang Cui, Vladan Radosavljevic, Thi Nguyen, Tzu-Kuo Huang, Matthew Niedoba, Jeff Schneider, Nemanja Djuric
Following detection and tracking of traffic actors, prediction of their future motion is the next critical component of a self-driving vehicle (SDV) technology, allowing the SDV to operate safely and efficiently in its environment.
no code implementations • 4 May 2019 • Liang Xiong, Xi Chen, Tzu-Kuo Huang, Jeff Schneider, Jaime G. Carbonell
Motivated by our sales prediction problem, we propose a factor-based algorithm that is able to take time into account.
2 code implementations • 18 Sep 2018 • Henggang Cui, Vladan Radosavljevic, Fang-Chieh Chou, Tsung-Han Lin, Thi Nguyen, Tzu-Kuo Huang, Jeff Schneider, Nemanja Djuric
Autonomous driving presents one of the largest problems that the robotics and artificial intelligence communities are facing at the moment, both in terms of difficulty and potential societal impact.
no code implementations • ICML 2017 • Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daume III, John Langford
We design an active learning algorithm for cost-sensitive multiclass classification: problems where different errors have different costs.
no code implementations • NeurIPS 2016 • Tzu-Kuo Huang, Lihong Li, Ara Vartanian, Saleema Amershi, Jerry Zhu
We present a theoretical analysis of active learning with more realistic interactions with human oracles.
no code implementations • NeurIPS 2015 • Tzu-Kuo Huang, Alekh Agarwal, Daniel J. Hsu, John Langford, Robert E. Schapire
We develop a new active learning algorithm for the streaming setting satisfying three important properties: 1) It provably works for any classifier representation and classification problem including those with severe noise.
no code implementations • NeurIPS 2013 • Tzu-Kuo Huang, Jeff Schneider
Under that framework, we identify reasonable assumptions on the generative process of non-sequence data, and propose learning algorithms based on the tensor decomposition method \cite{anandkumar2012tensor} to \textit{provably} recover first-order Markov models and hidden Markov models.
no code implementations • NeurIPS 2011 • Tzu-Kuo Huang, Jeff G. Schneider
Vector Auto-regressive models (VAR) are useful tools for analyzing time series data.