Brain-inspired AI with Human-like Intelligence
Research Scientist | CNAI, KAIST | Nov. 2019–Dec. 2023
- Led the design of a simulation model for cognitive brain development.
- Discovered that noise-tuning alignment of latent variables is a reliable predictor of generalization performance (CNS 2023).
- Investigated regional Lipschitz continuity and its role in the generalization-robustness trade-off.
- Proposed an invariant representation learning framework for stochastic neural networks inspired by metamerism in the human visual cortex.
Myoung Hoon Ha
Postdoctoral Researcher
My research focuses on neuroscience-inspired AI, with particular emphasis on predictive coding, iterative inference, and stable learning in deep architectures.