Durai Rajamanickam Source Confirmed

Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.

Researcher

University of Arkansas at Little Rock

faculty

20 pubs

Research Areas

Causal Inference and Deep Learning Advanced Neural Network Applications Causal Graphs and Estimation Machine Learning Theory and Algorithms

Is this your profile? Verify and claim your profile

OverviewAI-generated summary

Durai Rajamanickam's research focuses on the fundamental principles and applications of causal inference, particularly within the context of deep learning. His recent publications explore key concepts such as backdoor and frontdoor criteria, propensity scores, and causal graphs. These works aim to provide a comprehensive understanding of causal estimation basics and the application of do-calculus in complex systems.

Rajamanickam's scholarship also delves into the development and application of novel deep learning methodologies, specifically referencing CFRNet (Causal Representation Learning Network). This research investigates how causal inference can be integrated with deep learning to balance representations and enhance understanding of underlying causal relationships. His work contributes to the theoretical and practical advancements in causal deep learning.

Metrics

  • Publications: 20

Selected Publications

  • Backdoor and Frontdoor Criteria (2025) DOI
  • Introduction to Causal Thinking (2025) DOI
  • Summary of Key Concepts (2025) DOI
  • Propensity Scores in Causal Deep Learning (2025) DOI
  • Balancing Representations with Causal Deep Learning (CFRNet) (2025) DOI
  • Causal Graphs: Structure and Assumptions (2025) DOI
  • Causal Estimation Basics (2025) DOI
  • Introduction to Do-Calculus (2025) DOI
  • Case Studies (2025) DOI
  • Assumptions and Real-World Challenges in Causal Inference (2025) DOI
  • Evaluating Causal Models Without Counterfactuals (2025) DOI
  • Interventions and Counterfactuals (2025) DOI
  • Solutions to Exercises (2025) DOI
  • Treatments, Outcomes, and Confounding: Core Concepts (2025) DOI
  • Causal Inference Meets Deep Learning (2025) DOI