AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking

Shuchen Wu, Noemi Elteto, Ishita Dasgupta, Eric Schulz

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use HCM instead of an RNN to model human reaction timesHCM · Human reaction time regression (47 participants)regression coefficient beta: 9.24 -> 16.74Improved
use HCM instead of an RNN to model human reaction timesHCM · Human reaction time regression (47 participants)Kendall tau: 0.085 -> 0.165Improved
use HCM instead of an RNN to model human reaction timesHCM · Human reaction time regression (47 participants)BIC: 314236.4 -> 313586.5Improved
use HCM instead of a 3-layer RNN as the learner on hierarchical generative sequencesHCM · Synthetic hierarchical sequences, depths dKL divergence convergence speedImproved
increase depth of the generative hierarchyHCM versus RNN · Synthetic hierarchical sequencesdata-efficiency advantage over RNNImproved
pre-train HCM on an interfering environment before switchingHCM · Environment transferearly performance over first 500 trialsHurt
pre-train HCM on a facilitative environment before switchingHCM · Environment transferearly performance over first 500 trialsImproved
increase participant ageHCM · Resting-state fMRIaverage chunk size: r = 0.23Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy