no code implementations • 10 Sep 2023 • Siwen Yan, Phillip Odom, Sriraam Natarajan
We consider the problem of identifying authorship by posing it as a knowledge graph construction and refinement.
1 code implementation • 16 Dec 2019 • Alexander L. Hayes, Mayukh Das, Phillip Odom, Sriraam Natarajan
One of the key advantages of Inductive Logic Programming systems is the ability of the domain experts to provide background knowledge as modes that allow for efficient search through the space of hypotheses.
no code implementations • ICLR Workshop LLD 2019 • Phillip Odom, Aaron Keech, Zsolt Kira
Hierarchical reinforcement learning captures sub-task information to learn modular policies that can be quickly adapted to new tasks.
Constrained Clustering
Hierarchical Reinforcement Learning
+3
1 code implementation • ICLR 2019 • Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira
This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation.
no code implementations • 28 Jun 2018 • Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira
The proposed objective directly minimizes the negative log-likelihood of cluster assignment with respect to the pairwise constraints, has no hyper-parameters, and demonstrates improved scalability and performance on both supervised learning and unsupervised transfer learning.
Ranked #1 on
Ecg Risk Stratification
on ngm
no code implementations • 19 Apr 2018 • Mayukh Das, Phillip Odom, Md. Rakibul Islam, Janardhan Rao, Doppa, Dan Roth, Sriraam Natarajan
Planning with preferences has been employed extensively to quickly generate high-quality plans.