◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

T. Poggio

37 papers hereh-index 12686k citations676 works total

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

author position
  • first author6
  • middle author5
  • last author25

Across the 36 of 37 papers where every author was matched, so the position is known.

fields
  • cs.LG24
  • stat.ML4
  • cs.CV3
  • q-bio.NC2
  • cs.AI1
  • cs.NE1
same name
  • T. Poggio — 6 papers, h 5
  • T. Poggio — 1 paper, h 16

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
20132023
most citedTheory of Deep Learning III: explaining the non-overfitting puzzle

49 citations · 263 across the 22 of their papers we have counts for

collaborators
Showing 2017Show all

4 papers · 1 filter

cs.LG2017

Fisher-Rao Metric, Geometry, and Complexity of Neural Networks

Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin +1

We study the relationship between geometry and capacity measures for deep neural networks from an invariance viewpoint. We introduce a new notion of capacity --- the Fisher-Rao nor…

cs.CV2017★ 3 cited

Pruning Convolutional Neural Networks for Image Instance Retrieval

Gaurav Manek, Jie Lin, Vijay Chandrasekhar +4

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN). The objective is to heavily prune…

cs.CV2017★ 1 cited

Do Deep Neural Networks Suffer from Crowding?

Anna Volokitin, Gemma Roig, Tomaso Poggio

Crowding is a visual effect suffered by humans, in which an object that can be recognized in isolation can no longer be recognized when other objects, called flankers, are placed c…

cs.CV2017★ 4 cited

Compression of Deep Neural Networks for Image Instance Retrieval

Vijay Chandrasekhar, Jie Lin, Qianli Liao +4

Image instance retrieval is the problem of retrieving images from a database which contain the same object. Convolutional Neural Network (CNN) based descriptors are becoming the do…

◍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.