Jin Hwa Lee

profil_big.jpeg

Hi, I’m Jin (she/her)!

I am a PhD student at University College London supervised by Andrew Saxe.

At the moment, I am mainly intrigued by compositionality in learning and inference. While compositionality is very general capability that humans have in language acquisition, skill learning and generalization, current artificial intelligent systems do not exhibit the same level of compositional ability (or maybe they do?!).

How do humans discover useful motifs or concepts and flexibly reuse them to solve complex tasks?
How do we evaluate machines exhibiting compositional behavior? How does compositionality emerge during learning?

To answer these questions, I aim to study both biological brains and artificial neural networks.
I use artificial neural networks to model interesting cognitive/behavioural observations in humans and animals to bring quantitative understanding of the mechanism of intelligence..

Before starting my PhD journey, I obtained BSc. Physics at KAIST and I studied Neurosciece for my master, supervised by Mackenzie Mathis and developed CEBRA for my thesis.

See Research section for more on previous/ongoing projects.

news

Oct 8, 2024 We developed a theory about the exact conditions to learn modular representation in neural networks and brain; Don’t cut corners of source distribution! 📐
Oct 2, 2024 Our porject on analyzing phase transition in representational geometry in LLMs during the pre-training phase is out here.
Jul 20, 2024 I’m giving a tutorial talk in Conference on Lifelong Learning Agents! in August, Pisa. I’ll be talking about theoretical approaches in continual learning.
Jul 1, 2024 My first PhD project Why do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning is accepted to ICML 2024!
Sep 30, 2023 I joined Saxe Lab and started a PhD journey 🚀🧠 :))