Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Hardik Rajpal

Hardik Rajpal

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Neurons and Cognition×1Info Theory×1ML×1Neural Computing×1nlin.CD×1

Frequent co-authors

Dan Goodman1×

Research Timeline

2026
Emergent Generalization by Representation Learning in Artificial Neural Networks

The authors show that an explicit information bottleneck in a recurrent neural network is necessary for rotational and out-of-distribution generalization in a time-series prediction task, and that the emergence of structure in the representation scales with task complexity and predicts generalization performance.

Highlighted terms show continued research focus across papers

Papers

q-bio.NCcs.ITcs.LGEmpiricalRecentJul 11, 2026

Emergent Generalization by Representation Learning in Artificial Neural Networks

Hardik Rajpal, Dan Goodman

The authors show that an explicit information bottleneck in a recurrent neural network is necessary for rotational and out-of-distribution generalization in a time-series prediction task, and that the…

View →