Francesco Orabona's repositories
parameterfree
Parameter-Free Optimizers for Pytorch
FighterDroid2P
App to use the second joystick and its buttons in emulators on Arcade1up Fighter Droids. It works by associating the joystick movements to the keys of a virtual keyboard.
rnn-from-scratch
Use tensorflow's tf.scan to build vanilla, GRU and LSTM RNNs
A1AndroidControlFix
'emulates' a controller using data received from an Arcade1up joystick/button encoder on android based platforms, specifically designed for and tested on Simpsons, TMNT (In Time) and "Fighter Droids".
Crowded-Valley---Results
This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"
CSrankings
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
evaluate_vw
Python scripts to evaluate the performance of different VW algorithms on OpenML datasets
vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.