Kushin Mukherjee

My primary interest is in the nature of visual concepts. How are they learned? Why are they useful? Can machines be taught these concepts? I study drawings as a means to answer these questions.

I’m affiliated with the Knowledge and Concepts LabSchloss Visual Reasoning LabAusterweil Lab, and the Wisconsin Institute for Discovery. I grew up in Kolkata, India, a bustling city with hot summers and torrential monsoons. Noticing a distinct lack of snow in my climate collection, I moved to upstate New York, where I received my BA in Cognitive Science and Japanese from Vassar College.

While at Vassar, I was advised by Ken Livingston and Josh de Leeuw. I also spent a summer at the Computation and Cognition Lab at Stanford University as a CSLI intern, working with Judy Fan and Robert Hawkins.


Personal website:





Communicating semantic part information in drawings.

K Mukherjee, RXD Hawkins, JW Fan
CogSci, 2413-2419

Context matters: A theory of semantic discriminability for perceptual encoding systems

K Mukherjee, B Yin, BE Sherman, L Lessard, KB Schloss
IEEE Transactions on Visualization and Computer Graphics 28 (1), 697-706

Finding meaning in simple sketches: How do humans and deep networks compare?

K Mukherjee, TT Rogers
Journal of Vision 20 (11), 1026-1026

From Images to Symbols: Drawing as a Window into the Mind

K Mukherjee, H Huey, TT Rogers, JE Fan
Proceedings of the Annual Meeting of the Cognitive Science Society 44 (44)

Mapping a low-dimensional space for color-concept associations

K Mukherjee, TT Rogers, L Lessard, MB Gleicher, KB Schloss
Vision Research 151, 99-116

How does task structure shape representations in deep neural networks?

K Mukherjee, TT Rogers
NeurIPS 2020 Workshop SVRHM