Skip to content
View frasalvi's full-sized avatar
๐Ÿ’ญ
๐Ÿ’ญ

Highlights

  • Pro

Organizations

@epfl-dlab @epfl-ada @CS-433 @LLMPersuasion

Block or report frasalvi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
frasalvi/README.md

๐Ÿ‘‹ Hi there, I'm Francesco Salvi (he/him)

  • ๐ŸŽ“ MSc in Computational Science and Engineering at EPFL, Lausanne.
  • ๐ŸŽ“ BSc in Physics at University of Bologna (UniBo)
  • ๐Ÿ‘จโ€๐Ÿ’ป Focusing on Computational Social Science, Network science, Machine Learning, and Data Science.
  • โœจ Passionate about politics, hiking and board games.

๐Ÿ“ซ Let's connect!

Website LinkedIn Twitter GitHub Scholar

๐Ÿ”จ Projects highlights

  • Topical classification of Wikipedia images: Developing a hierarchical classifier for Wikipedia images, categorizing them only by their topic. Designed a set of linguistically motivated heuristics to associate images with training labels within a custom taxonomy. Collaboration between dlab and Wikimedia Research.
  • A data-driven Political Compass: Analyzed a dataset of ~180 milion quotations from news media from 2008 and 2020, leveraging Topic Extraction and Sentiment Analysis to infer a new Political Compass based on quotes from US politicians. Read our data story!
  • Disambiguating Voynich Manuscript transliterations: Fine-tuned word embedding models (fastText, word2vec) to disambiguate transliterations of the Voynich Manuscript, a mysterious medieval document written in a completely unknown script. Benchmarks were built for Italian and Latin with comparable scarce data, obtaining an accuracy of 86%.
  • (๐Ÿ‡ฎ๐Ÿ‡น) Effetti di congestione per modelli di traffico su rete stradale: uno studio su Bologna: Improved a traffic simulation on the Emilia-Romagna region using origin-destination data from TIM, extracting Macroscopic Fundamental Diagrams and investigating the effects of hysteresis and heterogeneity.

Pinned Loading

  1. Noise2Noise-Denoising-Autoencoder Noise2Noise-Denoising-Autoencoder Public

    Denoising Autoencoder trained with only noisy images, implemented both with PyTorch and from scratch.

    Jupyter Notebook 1

  2. DQL_Nim DQL_Nim Public

    Q-Learning and Deep Q-Learning agents learning to play Nim

    Jupyter Notebook

  3. twitter_hateful_users twitter_hateful_users Public

    Detecting Hateful Users on Twitter with Graph Machine Learning

    Jupyter Notebook 1

  4. n_queens_mcmc n_queens_mcmc Public

    Solving the N-queens problem via the Metropolis algorithm

    Jupyter Notebook 1

  5. epfl-dlab/wiki_image_classification epfl-dlab/wiki_image_classification Public

    Wikipedia Image Classification project

    Jupyter Notebook 2 2

  6. percolation-centrality percolation-centrality Public

    Critical review, reproduction and extension of Percolation Centrality

    Jupyter Notebook 1