Keynotes | K&Ts | GACs | Talks | Posters | Search

Poster F in Poster Session F: Thursday, August 6, 1:45 – 3:30 pm, Kimmel Center, Shorin & Rosenthal Rooms

HOLMES: Hierarchical Online Learning of Multiscale Experience Structure

Ines Aitsahalia¹, Kiyohito Iigaya¹; ¹Columbia University

Presenter: Ines Aitsahalia

Learning systems must balance generalization across experiences with discrimination of task-relevant details, requiring representations that support both. Online latent-cause models support incremental inference but assume flat partitions, whereas hierarchical Bayesian models capture multilevel structure but typically require offline inference. We introduce the Hierarchical Online Learning of Multiscale Experience Structure (HOLMES) model, a computational framework for hierarchical latent structure learning through online inference. HOLMES combines a variation on the nested Chinese Restaurant Process prior with sequential Monte Carlo inference to perform tractable trial-by-trial inference over hierarchical latent representations without explicit supervision. In simulations, HOLMES improved task accuracy and representational efficiency compared to the flat latent cause model. These results provide a tractable computational framework for discovering hierarchical structure in sequential data.

Topic Area: Memory, Learning & Knowledge Structures