Welcome!
I am a mathematician working on deep learning
Email: justinchadwickasher@gmail.com
GitHub: github.com/justincasher
LinkedIn: linkedin.com/in/justin-asher
Recent work
The need for an autoformalizer (2024)
Abstract. I argue that the creation of an autoformalizer—a machine that can verify mathematics—would have monumental benefits for both academic research and industrial applications. I then discuss how one could be created.
Modeling Catan using self-play (2024)
Abstract. I taught a neural network how to play the board game Catan using reinforcement learning via self-play. When training, I utilized both temporal-difference and Monte-Carlo tree search methods, along with a residual neural network structure. The resulting model achieved an intermediate level of play.
© 2024 • Justin Asher