Shanka Subhra Mondal

Google Scholar, CV, LinkedIn

Hi! I am a fifth-year Ph.D. student in Electrical and Computer Engineering at Princeton University advised by Jonathan D. Cohen. My research interests are computer vision, deep learning, abstract reasoning, and generalization in neural networks. Currently, I am working on developing artificial neural network models using mechanisms inspired by the human brain that can support out-of-distribution generalization. This summer, I interned at Microsoft Research, New York under Ida Momennejad. I also worked on a few projects with Sebastian Seung and Tom Griffiths. Before this, I was an undergrad at the Indian Institute of Technology, Kharagpur where I worked with Debdoot Sheet at the intersection of deep learning and biomedical imaging.

EDUCATION:

Ph.D. in Electrical and Computer Engineering. 2019-Present. Princeton University

M.A in Electrical and Computer Engineering. 2022. Princeton University

B.Tech in Electronics and Electrical Communication Engineering. 2015-2019. IIT Kharagpur

PUBLICATIONS:

A Prefrontal Cortex-inspired Architecture for Planning in Large Language Models

Shanka Subhra Mondal*, Taylor W. Webb*, Chi Wang, Brian Krabach, Ida Momennejad. (Under Review).

* equal contribution

Systematic Visual Reasoning through Object-Centric Relational Abstraction

Shanka Subhra Mondal*, Taylor W. Webb*, Jonathan D. Cohen. Advances in Neural Information Processing Systems (NeurIPS), 2023.

* equal contribution

Determinantal Point Process Attention Over Grid Codes Supports Extrapolation

Shanka Subhra Mondal, Steven M. Frankland, Taylor W. Webb, Jonathan D. Cohen. eLife, 2023.

Learning to reason over visual objects

Shanka Subhra Mondal*, Taylor W. Webb*, Jonathan D. Cohen. Proceedings of the 11th International Conference on Learning Representations (ICLR), 2023.

* equal contribution

Scheduling of time-varying workloads using reinforcement learning

Shanka Subhra Mondal*, Nikhil Sheoran*, Subrata Mitra. Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021.

* equal contribution

Self-learning scheduler for application orchestration on shared compute cluster

Subrata Mitra, Nikhil Sheoran, Ramanuja Simha, Shanka Subhra Mondal, Neeraj Dhake, Ravinder Nehra. US Patent, 2020.

Deepplace: Learning to place applications in multi-tenant clusters

Subrata Mitra, Shanka Subhra Mondal, Nikhil Sheoran, Neeraj Dhake, Ravinder Nehra, Ramanuja Simha. Proceedings of the 10th ACM SIGOPS Asia-Pacific Workshop on Systems, 2019.

Kinship verification using deep siamese convolutional neural network

Abhilash Nandy, Shanka Subhra Mondal. Proceedings of the 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG) Workshop, 2019.

Multitask learning of temporal connectionism in convolutional networks using a joint distribution loss function to simultaneously identify tools and phase in surgical videos

Shanka Subhra Mondal, Rachana Sathish, Debdoot Sheet. Proceedings of the 5th MedImage Workshop at 11th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2018.