Madhavun Candadai

Doctoral Candidate in Cognitive Science with minor in Computer Science at
Indiana University, Bloomington.

I am a doctoral candidate at Indiana University, Bloomington doing my Ph.D. in Cognitive Science, with a minor in Computer Science. My research interests lie at the intersection of Computational Neuroscience and Machine Learning. At Dr. Eduardo Izquierdo's lab, our work involves understanding the principles of information processing in neural networks. Specifically, using tools of information theory and dynamical systems theory, we study agents (neural networks) that are in continuous closed-loop interaction with their environment through actions. Insights from analyzing ensembles of solutions not only serve as hypotheses for the neural basis of natural behavior but also provide design ideas for artificially intelligent systems.

Areas of interest: Computational Neuroscience, Deep (Reinforcement) Learning, Evolutionary Computing, Unsupervised learning, Information Theory, Complex Systems, Dynamical Systems Theory, Artificial Life, Robotics


See Google Scholar or resume for a list of papers, talks and posters.

Computational Neuroscience / Cognitive Science

Candadai, Madhavun, and Eduardo J. Izquierdo. "Sources of predictive information in dynamical neural networks." (Under review)[preprint]
Candadai, Madhavun, Matthew Setzler, Eduardo J. Izquierdo, and Tom Froese. "Embodied dyadic interaction increases complexity of neural dynamics: A minimal agent-based simulation model." Frontiers in Psychology 10 (2019): 540. [pdf]
Vasu, Madhavun Candadai, and Eduardo J. Izquierdo. "Multifunctionality in embodied agents: Three levels of neural reuse." arXiv preprint arXiv:1802.03891 (2018). Proceedings of the 40th Cognitive Science Conference, 2018. [pdf]
Vasu, Madhavun Candadai , and Eduardo J. Izquierdo. "Information Bottleneck in Control Tasks with Recurrent Spiking Neural Networks". International Conference on Artificial Neural Networks. (ICANN) Springer, Cham, 2017. [pdf]
Vasu, Madhavun Candadai , and Eduardo J. Izquierdo. "Evolution and Analysis of Embodied Spiking Neural Networks Reveals Task-Specific Clusters of Effective Networks." In Proceedings of Genetic and Evolutionary Computing Conference, pp. 75-82. GECCO, 2017. [pdf]
Nominated for Best Student Paper, 2017, by International Society for Artificial Life: Student Chapter

Machine Learning / A.I.

Dwiel, Zach*, Madhavun Candadai*, Mariano J. Phielipp. (2019, November). On Training Flexible Robots using Deep Reinforcement Learning. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE. (Accepted) [pdf] (*equal contribution)
Dwiel, Zach, Madhavun Candadai, Mariano J. Phielipp, Arjun K. Bansal. "Hierarchical policy learning is sensitive to goal space design". In Task-Agnostic Reinforcement Learning Workshop (TARL), of International Conference on Learning Representations (ICLR), 2019. [pdf]
Candadai, Madhavun, Aashay Vanarase, Mei Mei, and Ali A. Minai. "ANSWER: An unsupervised attractor network method for detecting salient words in text corpora." In International Joint Conference on Neural Networks 2015, pp. 1-8. IEEE, 2015. [pdf]


Candadai, M., & Izquierdo, E. J. (2019). infotheory: A C++/Python package for multivariate information theoretic analysis. arXiv preprint arXiv:1907.02339. [pdf] (Under review at JOSS)

Education and Experience

Intel A.I. Lab - Intern

Summer 2018

Doctoral Candidate, Program in Cognitive Science
Indiana University, Bloomington.

2015 - present

Cincinnati Children's Hospital Medical Center


M.S. Electrical Engineering
University of Cincinnati


Associate System Engineer

2011 - 2012

B.Tech. Electronics and Communication Engineering
Amrita School of Engineering


Open Source Projects


A C++/Python package for information theoretic analysis.