◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

G. P. Leonardi

18 papers hereh-index 181.2k citations73 works total

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

author position
  • sole author1
  • first author8
  • middle author7
  • last author2

Across the 18 of 18 papers where every author was matched, so the position is known.

fields
  • math.AP5
  • cs.LG3
  • math.CA2
  • math.MG2
  • math.OC2
  • math.DG1

identity via Semantic Scholar / OpenAlex

activity
20102026
most citedAdditive Noise Annealing and Approximation Properties of Quantized Neural Networks

15 citations · 17 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

3 papers · 1 filter

cs.LG2022

Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm

Matteo Spallanzani, Gian Paolo Leonardi, Luca Benini

Training quantised neural networks (QNNs) is a non-differentiable optimisation problem since weights and features are output by piecewise constant functions. The standard solution…

cs.LG2020★ 1 cited

Analytical aspects of non-differentiable neural networks

Gian Paolo Leonardi, Matteo Spallanzani

Research in computational deep learning has directed considerable efforts towards hardware-oriented optimisations for deep neural networks, via the simplification of the activation…

cs.LG2019★ 15 cited

Additive Noise Annealing and Approximation Properties of Quantized Neural Networks

Matteo Spallanzani, Lukas Cavigelli, Gian Paolo Leonardi +2

We present a theoretical and experimental investigation of the quantization problem for artificial neural networks. We provide a mathematical definition of quantized neural network…

◍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.