pith. sign in

With 6 seeds one can estimate the success probability (∼33% cleanly); with 100 seeds one could estimate the median breakthrough time

— the Transformer must discover, via gradient descent, a specific attention-weight configuration that implements the online-learning algorithm, this discovery is a discrete phase transition with an unpredictable onset time · 2019 · arXiv 3150.9780

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.NE 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Dendritic In-Context Learning in a Single-Layer Spiking Neural Network

cs.NE · 2026-07-02 · unverdicted · novelty 8.0

A single-layer compartmental SNN with apical recurrence matching leaky online Widrow-Hoff LMS achieves seed-stable ICL on high-dimensional Garg-2022 tasks where Transformers fail, with a linear probe recovering the LMS trajectory at R²=0.93.

citing papers explorer

Showing 1 of 1 citing paper.

  • Dendritic In-Context Learning in a Single-Layer Spiking Neural Network cs.NE · 2026-07-02 · unverdicted · none · ref 8

    A single-layer compartmental SNN with apical recurrence matching leaky online Widrow-Hoff LMS achieves seed-stable ICL on high-dimensional Garg-2022 tasks where Transformers fail, with a linear probe recovering the LMS trajectory at R²=0.93.