◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

M. Magnasco

37 papers hereh-index 439.3k citations146 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • sole author4
  • first author1
  • middle author6
  • last author26

Across the 37 of 37 papers where every author was matched, so the position is known.

fields
  • physics.bio-ph8
  • q-bio.NC6
  • cond-mat.dis-nn4
  • nlin.CD4
  • cond-mat.stat-mech3
  • nlin.AO2

identity via Semantic Scholar / OpenAlex

activity
19992024
most citedEssential nonlinearities in hearing

412 citations · 2.3k across the 37 of their papers we have counts for

collaborators
Showing 2023Show all

1 paper · 1 filter

cs.LG2023★ 1 cited

Convolutional unitary or orthogonal recurrent neural networks

Marcelo O. Magnasco

Recurrent neural networks are extremely powerful yet hard to train. One of their issues is the vanishing gradient problem, whereby propagation of training signals may be exponentia…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.