Caleb Schultz Kisby
[My website is currently under construction, but the important links should still work.]
Welcome! I'm a computer scientist currently finishing my PhD at Indiana University. I am co-supervised by Larry Moss and Saúl Blanco. I'm also a member of the IU logic group and plwonks, and have participated in the IU Cognitive Lunch seminar.
Updates: I am finishing up my dissertation at last! Click here for an in-progress draft. I'm also on the job market, looking for opportunities to do interesting work with neuro-symbolic systems, dynamic logic, learning theory, proof assistants, formally verified code, or some combination of these things.
Contact: cckisby () gmail.com
How should we best integrate symbolic and neural (sub-symbolic) systems?
How can we extract, interpret, and verify the internal beliefs of neural networks?
How powerful and reliable are different learning algorithms, when compared to one another?
Is provably correct AI alignment possible?
I also enjoy using dependently-typed programming languages / proof assistants (e.g., Lean, Agda) to help write both my proofs and my code. These days, I'm growing more interested in developing new tools to make dependently-typed programming a viable option for working software engineers and mathematicians.
If you're looking for paper drafts, slides, or code, see the Pubs tab above. For a complete list of my research activity, see my cv.
This website was made using TeXmacs, based on Massimiliano Gubinelli's personal website.