Garrett Ethan Katz

Assistant Professor

Electrical Engineering and Computer Science

CST 4-189

gkatz01@syr.edu

315.443.3565

Degrees:

  • B.A. Philosophy, Cornell University, 2007
  • M.A. Mathematics, City College of New York, 2011
  • Ph.D. Computer Science, University of Maryland, College Park, 2017

Areas of Expertise:

  • Automated Planning and Reasoning
  • Robotic Manipulation and Imitation Learning
  • Neuro-Symbolic Programming
  • Numerical Path Following and Optimization

Current Research:

My research focuses on “vertically integrated” artificial intelligence, ranging from low-level robotic motor control and synaptic learning rules to high-level planning and abstract reasoning. My recent work has focused on single-pass learning, automated algorithm discovery, and neuro-symbolic robotic control.

Honors and Awards:

  • Best Paper Award at the 18th International Conference on Augmented Cognition at HCII, 2024
  • Best Paper Award at the SAI Computing Conference, 2020
  • Larry S. Davis Doctoral Dissertation Award, UMD, 2018
  • Best Student Paper Award at the 9th International Conference on Artificial General Intelligence 2016

Selected Publications:

  • Liu R, He B, Tahir N, Katz GE. On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors. In Forty-first International Conference on Machine Learning (ICML). 2024. PMLR.
  • Katz GE, Tahir N. Towards Automated Discovery of God-Like Folk Algorithms for Rubik’s Cube. In 2022 AAAI Conference on Artificial Intelligence. AAAI.
  • Katz GE, Akshay, Davis GP, Gentili RJ, Reggia JA. Tunable Neural Encoding of a Symbolic Robotic Manipulation Algorithm. Frontiers in Neurorobotics. 2021:167.
  • Tahir N, Katz GE. Numerical Exploration of Training Loss Level-Sets in Deep Neural Networks. In 2021 International Joint Conference on Neural Networks (IJCNN) 2021 (pp. 1-8). IEEE.
  • Katz GE, Reggia JA. Using directional fibers to locate fixed points of recurrent neural networks. IEEE Transactions on Neural Networks and Learning Systems. 2017 Aug 24;29(8):3636-46.