I am a computer scientist and mathematician from Salt Lake City, Utah. I currently study at UC Berkeley and work part-time at Bonsai AI making AI that use other AI to solve problems. A large part of my time is devoted to Machine Learning at Berkeley (ML@B), a research/consulting organizaton I cofounded in 2015. [bio]
My goal is to understand human intelligence by creating artificial intelligence.
Deep Function Machines: Generalized Neural Networks for Topological Layer Expression. William H. Guss. COLT 2017 (Submitting). [arXiv]
Universal Approximation of Nonlinear Operators on Banach Space. William H. Guss. Machine Learning at Berkeley Research Symposium 2016. [pdf]
Backpropagation-Free Parallel Deep Reinforcement Learning. William H. Guss. James Bartlett, Noah Golmant, Phillip Kuznetsov, Max Johansen. NIPS 2017 (WIP). [pdf]
Parameter Reduction using Operator Neural Networks. William H. Guss. Microsoft Research Symposium 2016. Best Poster Award. [pdf]
Functional Neural Networks Evaluated by Weierstrass Polynomials. William H. Guss, Phillip Kuznetsov, Patrick Chen. Intel ISEF 2015. Pittsburgh, Pennsylvania. [AAAI’ Honorable Mention] [ASA’ Honorable Mention]