Nithin Raghavan

I am an undergraduate at UC Berkeley double-majoring in Computer Science and Applied Mathematics. I'm also part of Ren Ng's group, which is a part of the Berkeley AI Research Group.

At Berkeley I have taken a variety of courses and worked on a number of interesting personal projects. My research interests include deep learning optimization, graphics, hardware acceleration and parallelization. Additionally, I have experience with systems administration, network systems and game development.

Email  /  Resume  /  LinkedIn  /  GitHub  /  Google Scholar

profile photo

* denotes equal contribution co-authorship

profile photo
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Matthew Tancik*, Pratul Srinivasan*, Ben Mildenhall*, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, Ren Ng
NeurIPS, 2020 (Spotlight)
project page / arXiv / code

Mapping input coordinates with simple Fourier features before passing them to a fully-connected network enables the network to learn much higher-frequency functions.

Ford Motor Company
Research Intern
Samsung Advanced Computing Lab
Research Intern
Personal Projects
Compressed Sensing
Computes LASSO on the matrix-vector product representation of the discrete wavelet transform of an input signal with orthogonal Daubechies wavelets for compression and data preprocessing
Software Renderer
Basic software rasterizer and renderer (requires SDL2). Capable of barycentric interpolation, backface culling and block-based rasterization.
Resource-Provisioning GPU Server
Currently leading a team of students to administrate and maintain a GPU cluster

Template borrowed from Jon Barron's website.