Contact Info
Name: Garrett Ethan Katz
Title: Assistant Professor
Department: Electrical Engineering & Computer Science
Office: CST 4-189, Syracuse University
Telephone: (315) 443-3565
Personal site:

I teach and research various topics in artificial intelligence, cognitive modeling, machine learning, neural computation, optimization, and robotics. Some representative examples are given below. Here are my C.V. and Google scholar profile.


CIS 467/667: Introduction to Artificial Intelligence
This course covers classical tree search algorithms like iterative deepening, A*, and minimax; probabilistic methods like MLE, MAP, and expectation maximization, stochastic models such as HMMs and MDPs, reinforcement learning methods such as Q-learning and policy gradient, basics of neural networks and gradient descent, and automated reasoning methods such as forward chaining, unification, and resolution.

CIS 700: Neural Program Learning
This special topics course surveys recent papers about neural networks that are trained to solve algorithmic tasks that are more traditionally accomplished by conventional computer programs. For example, these tasks require neural networks to represent/support constructs such as conditional branching, for/while loops, variable binding, random-access memory, and/or complex data structures.


Robotic imitation learning
CERIL is a cognitive robotics framework that uses Cause-Effect Reasoning to do Imitation Learning. Here is code and a paper describing the framework. CERIL uses traditional symbolic reasoning algorithms, but a Neural Virtual Machine that can emulate symbolic algorithms with neural computation is being used to re-implement CERIL. Here is code and a paper describing the NVM.
Directional fiber optimization
Directional fibers are a mathematical construct useful for numerically enumerating many distinct solutions to a system of non-linear equations, such as fixed points of dynamical systems or stationary points of objective functions. Here is code and two papers about the method.
Cryo-electron Microscopy
Bayesian inference techniques are applied to cryo-electron micrographs of biological virus particles to determine their 3D structure and understand their molecular machinery. Here is a paper applying these methods to cystovirus.