◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Razvan Pascanu

Google DeepMind

119 papers hereh-index 7957.8k citations209 works total

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

author position
  • first author3
  • middle author83
  • last author24

Across the 110 of 119 papers where every author was matched, so the position is known.

fields
  • cs.LG80
  • cs.CL14
  • stat.ML11
  • cs.AI5
  • cs.CV4
  • cs.NE3
affiliations
  • Google DeepMind
Homepage
same name
  • Razvan Pascanu — 7 papers
  • Razvan Pascanu — 5 papers, h 1

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20112026
most citedOn the difficulty of training Recurrent Neural Networks

3.8k citations · 6.6k across the 73 of their papers we have counts for

collaborators
Showing cs.NEShow all

3 papers · 1 filter

cs.NE2019

Improving the Gating Mechanism of Recurrent Neural Networks

Albert Gu, Caglar Gulcehre, Tom Le Paine +2

Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introd…

cs.NE2018

Hyperbolic Attention Networks

Caglar Gulcehre, Misha Denil, Mateusz Malinowski +8

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure. A few recent app…

cs.NE2018

Model compression via distillation and quantization

Antonio Polino, Razvan Pascanu, Dan Alistarh

Deep neural networks (DNNs) continue to make significant advances, solving tasks from image classification to translation or reinforcement learning. One aspect of the field receivi…

◍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.