M Ganeshkumar

Welcome to Ganesh’s page!

[New Preprint Alert! Kumar, M. G., Bordelon, B., Zavatone-Veth, J., Pehlevan, C. (2024). A Model of Place Field Reorganization During Reward Maximization.]

Research interests

As we experience the world, our brain learns internal models of the world so that we can solve new problems quickly. How do neural circuits and algorithms learn these models, and how do we decide the next best action? It has also been proposed that distortions to these internal models and learning algorithms contribute to psychiatric disorders. Can we develop mathematical models to understand these phenomena? Can we improve existing artificial systems and devise tools to alleivate disorders?

To explore these questions, I develop artificially intelligent agents, grounded to theory and experiments, to understand learning computations for intelligence, and when it might fail. Based on these insights, I hope to improve existing artificial systems, and develop technologies that can improve learning outcomes and alleviate learning disabilities.

Research background

Currently, I am a postdoctoral fellow in the Harvard Machine Learning Foundations Group, developing reinforcement learning agents to understand representational learning in biological and artificial systems. I am advised by Cengiz Pehlevan, Demba Ba, Lucas Janson and Boaz Barak.

Previously, I was a research scientist at the Centre for Frontier AI Research (CFAR), A*STAR developing vision-language reasoning datasets and models. I was advised by Cheston Tan.

In 2022, I completed my Ph.D. in Computational Neuroscience at the National University of Singapore (NUS) under the Integrative Sciences and Engineering Programme (ISEP). My doctoral thesis was to develop a biologically plausible reinforcement learning agent that learned new paired associations after a single example. I was co-advised by Andrew Tan and Shih-Cheng Yen and collaborated with Camilo Libedinsky.

I completed my B.Sc in Life Sciences in 2017 at the National University of Singapore where I worked on Brain-Computer Interfaces to control wheelchair using either human EEG or macaque intracortical spike data.

Besides research, I co-founded Nugen.ai that hopes to characterize affective states during learning to aid parents and teachers in personalizing education. I also love to tour either on my motorcycle or backpacking, and be involved in the arts scene.

Experience

Selected Full Publications

Conferences

Awards

Contact

Look forward to connecting with you!