Chandan Singh


I'm a PhD student at UC Berkeley exploring the intersection of computer science and neuroscience. My research interests are in computational neuroscience, deep learning, and interpretability.


Biological neurons Connectomics
Interpreting neural nets Vision

“Linearization of excitatory synaptic integration at no extra cost”, Morel, Singh, & Levy, 2018, Journal of Computational Neuroscience

“A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs”, Funke, Tschopp, Grisaitis, Singh, Saalfeld, & Turaga, 2017, arXiv

“A constrained, weighted-l1 minimization approach for joint discovery of heterogeneous neural connectivity graphs” - Singh, Wang, & Qi, 2017, NIPS 2017 Workshop on Advances in Modeling and Learning Interactions from Complex Data.

“A consensus layer V pyramidal neuron can sustain interpulse-interval coding” - Singh & Levy, 2017, Plos One.


  • Fall 2017 - Present

    UC Berkeley

    PhD student in Computer Science advised by Bin Yu.

  • Worked on unsupervised pretraining of CNNs for semantic segmentation.

  • Fall 2016 - Spring 2017

    UVA Yanjun Qi Research Lab

    Contributed to development of novel weighted-L1, multi-task Gaussian graphical models

  • Summer 2015, Winter 2015, Summer 2016

    HHMI Srini Turaga Lab

    Contributed to enhanced ML implementations for neural image segmentation

  • Fall 2014 - Fall 2016

    UVA William Levy Lab

    Simulated stochastic neurons to determine mutual information, variability, energy efficiency, and threshold

  • Simulated extracellular neural recordings via Neurocube Matlab scripts

  • Summer 2013 - Spring 2014


    Developed a web application + Android app for simultaneous task coordination + increasing the data storage capacity of QR codes.