Alexander Ku
I'm a PhD student at Princeton University (Psychology & Neuroscience), advised by
Tom Griffiths and
Jon Cohen, and a part-time Research Scientist at Google DeepMind.
I study learning and abstraction in neural networks,
with a focus on the tradeoff between representational flexibility and efficiency.
My recent work investigates how neural systems optimize this tradeoff across different time scales.
I approach these topics from the perspective of rational (Bayesian) analysis, meta-learning, and information theory.
Email /
Google Scholar /
GitHub /
Twitter /
CV