activity
20162021
most citedUser Friendly Automatic Construction of Background Knowledge: Mode Construction from ER Diagrams

8 citations · 12 across the 10 of their papers we have counts for

collaborators

13 papers

cs.LG2021

Relational Neural Markov Random Fields

Yuqiao Chen, Sriraam Natarajan, Nicholas Ruozzi

Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these mode…

cs.AI2021

Dynamic probabilistic logic models for effective abstractions in RL

Harsha Kokel, Arjun Manoharan, Sriraam Natarajan +2

State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hie…

cs.AI2020

A Preliminary Approach for Learning Relational Policies for the Management of Critically Ill Children

Michael A. Skinner, Lakshmi Raman, Neel Shah +2

The increased use of electronic health records has made possible the automated extraction of medical policies from patient records to aid in the development of clinical decision su…

cs.LG2020

Non-Parametric Learning of Lifted Restricted Boltzmann Machines

Navdeep Kaur, Gautam Kunapuli, Sriraam Natarajan

We consider the problem of discriminatively learning restricted Boltzmann machines in the presence of relational data. Unlike previous approaches that employ a rule learner (for st…

cs.AI20198 cited

User Friendly Automatic Construction of Background Knowledge: Mode Construction from ER Diagrams

Alexander L. Hayes, Mayukh Das, Phillip Odom +1

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 throu…

cs.LG2019

Neural Networks for Relational Data

Navdeep Kaur, Gautam Kunapuli, Saket Joshi +2

While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domain…