Personal Website

Connor Bybee

Reveal Contact Info

Postdoctoral Fellow

Neuroscience

Olshausen Lab
Sommer Lab

Current Research

I’m interested in artificial intelligence, machine learning, computer engineering, and neuroscience. Current and past projects include developing neural networks that optimize hard problems, efficient hardware implementations of neural networks, increasing the representational capacity of neural networks based on information theory, and developing computational theories for neuroscience. 

A key part of my work is dedicated to designing neural network algorithms that optimize nonlinear and combinatorial objective functions related to perception, operations research, decision-making, planning, protein design, logistics, finance, and engineering.

Another important research topic is addressing the need for efficient computing systems, specifically regarding latency, power consumption, and accuracy. The codesign of algorithms and hardware is one of the most important challenges of our time as the energy demands of current AI and ML hardware escalate, posing risks to the environment and accessibility. My research prioritizes the exploration of new computing technologies informed by algorithmic breakthroughs and emerging devices. 

All together, this work has implications for improving artificial systems and deepening our understanding of biological computation, bridging research in biology and the design of engineered systems.

Professional Positions

  • 2023 Postdoctoral Researcher, Olshausen Lab, University of California, Berkeley
    • Advisor: Prof. Bruno Olshausen
  • 2019 Jun-Dec Algorithms Software Engineer, Neuromorphic Computing Lab, Intel Labs, Intel, Hillsboro, OR
  • 2008-2015 Project Manager, Staff Engineer, California Resources Corporation/Occidental Petroleum 
    • 2013-2015 Production/Operations Engineer
    • 2011-2013 Project Manager/Facilities Engineer
    • 2008-2010 Engineering Intern
  • 2007-2010 Undergraduate Researcher, Pharmaceutical Chemistry Laboratory, University of Kansas

Education

  • 2022 Ph.D., Redwood Center for Theoretical Neuroscience, Computational Biology, University of California, Berkeley
    • Thesis: Oscillatory Neural Systems
    • Academic Advisor: Prof. Friedrich Sommer
  • 2017 MS, Computer Engineering, University of Southern California
  • 2011 BS, Chemical Engineering, University of Kansas

Awards and Funding

  • 2023 Schwartz Foundation Postdoctoral Fellowship for Theoretical Neuroscience
  • 2021 Intel Transformative Hardware for Artificial Intelligence grant
  • 2017-2019 National Science Foundation Graduate Research Fellowship Program

Journal & Conference Publications

  • Kymn, C. J., Kleyko, D., Frady, E. P., Bybee, C., Kanerva, P., Sommer, F. T., & Olshausen, B. A. (2023). Computing with Residue Numbers in High-Dimensional Representation. ArXiv.
  • Bybee, C., Kleyko, D., Nikonov, D. E., Khosrowshahi, A., Olshausen, B. A., & Sommer, F. T. (2023). Efficient optimization with higher-order Ising machines.  Nature Communications
  • Kleyko, D., Bybee, C., Huang, P. C., Kymn, C. J., Olshausen, B. A., Frady, E. P., & Sommer, F. T. (2023). Efficient decoding of compositional structure in holistic representations. Neural Computation, 35(7), 1159-1186.
  • Bybee, C., Sommer, F., Optimal Oscillator Memory Networks, Neuro-Inspired Computational Elements Workshop (NICE) 2022, Association for Computing Machinery (ACM) International Conference Proceedings Series. (2022)
  • Bybee, C., Belsten, A., Sommer, F., Cross-Frequency Coupling Increases Memory Capacity in Oscillatory Neural Networks, Computational and Systems Neuroscience (COSYNE) Conference (2022)
  • Rueckhaur, B., Bybee, C., Goettsche, U., Singh, Y., Mishra, J., and Wild, A., (In-Review) NxTF: An API and Compiler for Deep Spiking Neural Networks on Intel Loihi
  • Bybee, Connor, E. Paxon Frady, and Friedrich T. Sommer. “Deep Learning in Spiking Phasor Neural Networks.” arXiv preprint arXiv:2204.00507 (2022).
  • C Plumley, EM Gorman, N. El-Gendy, CR Bybee, EJ Munson, C Berkland. “Nifedipine Nanoparticle Agglomeration as a Dry Powder Aerosol Formulation Strategy” Int J Pharm. Mar 18, 2009; 369(1-2): 136–143.