The Murphy Lab
Shaping information with machine learning.
Hello and welcome!
We are a research group focused on designing information processing systems around lossy compression. We study the fundamentals of representation learning and information theory, and build algorithms that distill high-dimensional data into reduced descriptions.
If you’re curious about how to design and understand AI systems, consider joining! Openings for students at all levels, please reach out.
About me: I am now an assistant professor in the computer science department at NJIT!
A highly compressed view of my research trajectory:
New Jersey Institute of Technology Assistant Professor, 2025-
University of Pennsylvania Postdoc, 2021-2025
Google Research AI Resident, 2019-2021
University of Chicago PhD (Physics), 2013-2019
Lawrence Berkeley National Lab Research assistant, 2012-2013
UC Berkeley BA (Physics, computer science), 2009-2013
Visualization can be a powerful route to building intuition around how complex systems work. Below is a visualization of a randomly initialized neural network that warps two-dimensional space. The input starts as a square and then what you’re seeing is the square after passing through the network. Try varying the number of layers (64 units each) and the activation function!
Number of layers: