Alberto Tonda's repositories
Influence-Maximization
Code and data for experiments with evolutionary influence maximization
deep-learning-coronavirus-genome
Repository with data and code for the paper "Identification of SARS-CoV-2 from Genome Sequences using Deep Learning"
ensemble-feature-selection
Code and datasets for the (Lopez et. al, 2018) paper, currently under review.
symbolic-regression-conformal-prediction
Using symbolic regression to automatically discover functions for normalized conformal regresors.
random-adventure-plot-generator
Generate a list of TV tropes, monsters, locations (and maybe more), drawn from random tables, to be used for inspiration in writing a D&D (or other fantasy RPG) adventure.
prototype-set-discovery
Code and references related to prototype/representative set discovery
soft-sensor-pipe-fouling
Data and scripts to reproduce the experiments published in "Development of a Soft Sensor for Fouling Prediction in Pipe Fittings using the Example of Particulate Deposition from Suspension Flow"
clustering-thierry
Clustering experiments with Thierry Thomas-Danguin's data.
comparaison-grilles-salariels-fonction-publique-francaise
Projet pour comparer les grilles salarierls
ea-cluster-alejandro
EA for the experiments with Alejandro, for GECCO 2020
evolutionary-viability-theory
Repository for the experiments on EAs applied to viability theory
ffx
Fast Function Extraction
HumanModels
Classes for human-designed classifiers and regressors, scikit-learn compatible.
hydrology-bourgin
Data and experiments on the hydrological data sent by François Bourgin for the Summer School 2024.
inspyred
Python library for bio-inspired computational intelligence (modify plus replacement)
mo-insect-chain
Code for the multi-objective optimization of sustainable insect chains
optimization-crop-allocation
Multi-objective optimization of large-scale crop allocation
primer3-py
Simple oligo analysis and primer design
SashaShieldsIoDebugging
Repository for debugging shields.io badges
scikit-learn-naive
Updated (and re-indented) version of the "naive" scripts for scikit-learn