Communicating with Computers
The vision of this project (under the DARPA CwC grant) is to build smart machines that enable “Artificial Intelligence” agents and humans to interact seamles...
Posts by Category
HAAI
Closing the loop
The crux of human-allied smart machines lie in their capability to communicate back to the human, be it for sharing knowledge, for querying additional guidan...
Knowledge-intensive Gradient Boosting
Harsha Kokel, Phillip Odom, Shuo Yang, and Sriraam Natarajan Code Paper Appendix Poster
Human-guided Collaborative Problem Solving
Lara -- an integrated system of learning, reasoning and communication Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Naraya...
Knowledge-based Learning
Knowledge-rich approaches to learning and sequential decision-making try to alleviate the limitations of data-driven techniques caused by noise, stochastic...
applications
Natural Language Processing
Natural language processing is a hard task for traditional machine learning models, since they tend to ignore the relationships between the sentences, words,...
Logistics
Machine Learning is a natural choice in the Logistics domain for various problems like predicting the mode of movements of goods i.e. rail vs. road, predicti...
efficient-starai
Boosting
Statistical Relational Learning models combine the representational power of first-order logic with the ability of probability theory to handle uncertainity...
Scaling
We develop methodologies for fast approximate counting for scalable Statistical Relational AI. In the age of ‘Big Data’, scalability is one of the key challe...
Lifted Continuous Inference
Continuous values are common in the real world, but in traditional graphical model, inference with continuous variable may require computing integals of pote...
Lifted Deep Models
Relational Connectionist Models bring together the complementary strengths of scalability and explainability. Moreover, considering relational aspect of data...
RePReL
Integrating Relational Planning and Reinforcement Learning for Effective Abstraction Harsha Kokel, Arjun Manoharan, Sriraam Natarajan, Balaraman Ravindran, P...
Hybrid Deep RePReL
Integrating Relational Planning and Reinforcement Learning for Information Fusion Harsha Kokel, Nikhilesh Prabhakar, Balaraman Ravindran, Eric Blasch, Prasad...
Lifted/Relational Reinforcement Learning
The high level overview of this project is to build relational models for sequential decision making. The main bottleneck of approximating utility functions ...
precision-health
Adverse Drug-Events
With the increase in the number of drug discoveries and thus the data associated with each drug, detecting when these new drugs (and the old drugs) with reac...
Alzheimer’s and Parkinson’s Prediction
Progressive neurological diseases are untreatable and thus the only way of preventing these disease is to detect them early. This early detection is difficul...
Cardia
The Coronary Artery Risk Development in Young Adults (CARDIA) study is to identify the risk factors in early life that have influence on the development of c...
Automatic Operation Notes
With the explosion in the volume of medical information, there is the promise that patient care can be managed more precisely based on automatic extraction a...
Active elicitation of lab tests
The high level idea of this project is to actively elicit features for the most useful instances in order to build a sample efficient predictive model. We co...
Survey data
Survey data can be a rich source of information about non-clinical risk factors that could potentially have a considerable influence on the medical condition...
A Probabilistic Approach to Extract Qualitative Knowledge for Early Prediction of Gestational Diabetes
Athresh Karanam, Alexander L. Hayes, Harsha Kokel, David M. Haas, Predrag Radivojac, Sriraam Natarajan Paper Appendix Video
Explaining Deep Tractable Probabilistic Models: The sum-product network case
Athresh Karanam, Saurabh Mathur, Predrag Radivojac, David M. Haas, Kristian Kersting, Sriraam Natarajan Paper Appendix Code Poster Video
research-highlights
Saurabh Mathur: “Knowledge Intensive Learning of Cutset Networks”
My recent work deals with learning probabilistic models using expert advice. Specifically, we focus on a class of probabilistic models called cutset networks...
Siwen Yan: “Efficient Learning of Fair Models using Human Guidance and Privileged Information”
My recent research is centered around developing tree-based ensemble models and utilizing large language models. To enhance the performance and fairness of o...
Srijita Das: “Active Learning from Minimum Information”
My research focus has been on learning robust machine learning models from small pool of complete instances. A practical application of this has been in find...
Navdeep Kaur: “Relational Connectionist Models”
Relational Connectionist Models bring together the complementary strengths of scalability and interpretability. We have considered learning Boltzmann machine...
Nandini Ramanan: “Precision Health”
We aim to bridge the gap between the machine learning community and the existing applications to healthcare. Our work involves developing efficient algorithm...
Mayukh Das: “Human-Allied Problem Solving and Planning”
Knowledge-augmented approaches to sequential decision-making try to alleviate the limitations of data-driven techniques caused by noise, stochasticity and as...
Devendra Singh Dhami: “Structure-based Discovery of Drug-Drug Interactions”
I am currently working on the problem of drug-drug interactions using structural data from the molecules and chemical reaction pathways which exist between i...
Alexander L. Hayes: “Relation Extraction for Relational Learning”
My work is mostly centered on relational approaches to natural language processing. Approaches such as word2vec have increased interest in the context that w...