◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Soham De

DeepMind

16 papers hereh-index 263.9k citations39 works total

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

author position
  • first author3
  • middle author9
  • last author4

Across the 16 of 16 papers where every author was matched, so the position is known.

fields
  • cs.LG10
  • cs.CV2
  • stat.ML2
  • cs.SI1
  • q-bio.PE1
affiliations
  • DeepMind
Homepage
same name
  • Soham De — 10 papers, h 9
  • Soham De — 5 papers, h 2
  • Soham De — 4 papers

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
20172023
most citedHigh-Performance Large-Scale Image Recognition Without Normalization

256 citations · 457 across the 8 of their papers we have counts for

collaborators
Showing 2020Show all

4 papers · 1 filter

stat.ML2020

BYOL works even without batch statistics

Pierre H. Richemond, Jean-Bastien Grill, Florent Altché +8

Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation. From an augmented view of an image, BYOL trains an online network to predict a tar…

cs.LG2020★ 22 cited

On the Generalization Benefit of Noise in Stochastic Gradient Descent

Samuel L. Smith, Erich Elsen, Soham De

It has long been argued that minibatch stochastic gradient descent can generalize better than large batch gradient descent in deep neural networks. However recent papers have quest…

cs.SI2020

Modeling Citation Trajectories of Scientific Papers

Dattatreya Mohapatra, Siddharth Pal, Soham De +2

Several network growth models have been proposed in the literature that attempt to incorporate properties of citation networks. Generally, these models aim at retaining the degree…

cs.LG2020

Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks

Soham De, Samuel L. Smith

Batch normalization dramatically increases the largest trainable depth of residual networks, and this benefit has been crucial to the empirical success of deep residual networks on…

◍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.