Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.2% · Nov 201419922001200920182026
3 results for “sign-symmetry”
Biologically-plausible learning algorithms can scale to large datasetscs.LG

Biologically plausible learning algorithms can match BP on large datasets.

problem Learning algorithms that are biologically plausible often perform poorly on large datasets.
method Evaluation of sign-symmetry and feedback alignment algorithms on ImageNet and MS COCO.
result Sign-symmetry algorithm can match BP performance on ImageNet and MS COCO.
biologically plausible learningsign-symmetryfeedback alignmentImageNetCOCO
2018-11-08abs ↗pdf ↗
Learning with Algebraic Invariances, and the Invariant Kernel Trickstat.ML

When solving data analysis problems it is important to integrate prior knowledge and/or structural invariances. This paper contributes by a novel framework for incorporating algebraic invariance structure into kernels. In particular, we show that algebraic properties such as sign symmetries in data, phase independence,…

2014-11-28abs ↗pdf ↗
Deep Learning without Weight Transportcs.LG

New algorithms avoid weight transport, outperforming current deep learning methods.

problem Current deep learning algorithms rely on weight transport, which is biologically implausible.
method Two mechanisms: weight mirror and modified Kolen-Pollack algorithm, using random feedback weights.
result These mechanisms outperform feedback alignment and other methods on visual recognition tasks.
deep learningweight transportfeedback alignmentneural circuitsimage recognition
2019-04-10abs ↗pdf ↗