Antonio Vergari

Reader (Associate Professor) In Machine Learning At The University Of Edinburgh

City of Edinburgh, Scotland, United Kingdom
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Antonio Vergari is a Reader (Associate Professor) in Machine Learning at the University of Edinburgh with 15 years of experience building reliable probabilistic ML systems that blend rich symbolic reasoning with efficient deep learning inference. As PI of the APRIL lab he focuses on tractable probabilistic models and provable reliability in real-world settings, pushing NeSy (neuro-symbolic) approaches toward practical deployment. His background spans top research institutions (UCLA, Max Planck) and applied roles from clinical data management to generative design, reflecting a rare mix of theoretical depth and practical engineering. A top-graduated computer scientist from Università di Bari, he brings an interdisciplinary perspective and a taste for simplicity—selfie non multiplicanda praeter necessitatem—when designing scalable, interpretable ML.
code15 years of coding experience
job7 years of employment as a software developer
bookMaster's degree, Computer Science, 110/110 cum laude and special commendation by the commission, Master's degree, Computer Science, 110/110 cum laude and special commendation by the commission at Università degli Studi di Bari
github-logo-circle

Github Skills (96)

probabilistic-programming10
mixture-model10
autoencoder10
sum10
spn10
distributions10
information-theory10
bayesian10
probabilistic-models10
sum-product10
probabilistic-graphical-models10
graphical-models9
ai9
python9
encoding9

Programming languages (8)

JuliaC++CSSCSCSSHTMLJupyter NotebookPython

Github contributions (5)

github-logo-circle
arranger1044/MADE

Nov 2015 - Apr 2019

Contributions:59 pushes in 3 years 6 months
autoencodermachine-learningestimationmaskeddistribution
arranger1044/DEBD

Nov 2015 - Jul 2019

A collection of commonly used datasets as benchmarks for density estimation in MaLe
Contributions:15 commits, 2 PRs, 12 pushes in 3 years 8 months
density-estimation
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial