Image for post
Image for post

Published on the page “Fitting functions with a configurable XGBoost regressor”.

The page deals with the approximation of scalar mathematical functions to one or more real variables using a #xgboost regressor without writing code but only acting on the command line of Python scripts; the goal is to demonstrate that regression with XGBoost achieve low error values with extremely short learning times.

Here the url to the page:

Here is the url to the source code on GitHub:

Image for post
Image for post

Pubblicata sul sito la pagina “Approssimazione di funzioni tramite un regressore XGBoost configurabile”.

La pagina tratta dell’approssimazione di funzioni matematiche scalari a una o più variabili reali tramite un regressore #xgboost senza scrivere codice ma agendo solamente sulla linea di comando di script Python; l’obiettivo è di dimostrare che l’approssimazione di funzioni con XGBoost raggiungere bassi valori di errore con tempi di learning estremamente brevi.

Qui l’url alla pagina

Qui l’url ai sorgenti su GitHub:

Image for post
Image for post

The first post on time series was published on

The post deals with the forecast of univariate and equally spaced time series using a suite of programs written in Python to perform experiments on this type of series using different neural network taxonomies implemented with TensorFlow 2.x; all this without writing code but only acting on the command line of the programs in the suite itself.

At this link for details:

The full suite code, freely distributed on GitHub under the MIT license, is available for download at this link:

«From Science comes Prevision; from Prevision comes Action.»
(Auguste Comte)


Ettore Messina

I am the author of a website that deals with computation in general and neural networks and quantum programming in particular.