Facebook Twitter Instagram YouTube Channel

Bonaccorso’s Law

“Science is a beautiful gift to humanity; we should not distort it.”

(A. P. J. Abdul Kalam)

 

Machine learning copes with data. All scenarios: supervised, semi-supervised, unsupervised, and reinforcement-based extract pieces of information from the data and try to generalize the rules they learn when unseen samples are presented. Even if it can be either a limitation or something undeniable, I’ve formalized a concept I consider a pillar of any Artificial Intelligence research:

 

A natural or artificial intelligent agent can learn only what is already encoded in the data it perceives.

Giuseppe Bonaccorso

 

Another statement that I consider almost essential for Machine Learning is:

If a programming language needs more than one line of code to show “Hello World”, it will be probably a bad choice for Machine Learning.

Giuseppe Bonaccorso

 

Share this post on:
FacebookTwitterPinterestEmail

Related Posts

  • Crash-Introduction to Reinforcement Learning

    This keynote presentation has been prepared for a technical podcast and is meant to be a rapid (but relatively comprehensive) introduction to the essential concepts of Reinforcement Learning. Summary note on Reinforcement Learning Reinforcement Learning is a type of machine learning in which an agent learns to make decisions by…

  • My Technical Books

    “One day I will find the right words, and they will be simple.” (J. Kerouac)    Google Scholar Profile All the books are initially in English, but some translations are also available. If you have some of them, please consider also the Errata Corrige page. I no longer deal with…

  • Essays

    This is the main index for all the essays (mainly originally in Italian) written by Giuseppe Bonaccorso and often published in specialized magazines. They include literature, music, poetry, and philosophy essays.   If you need a specific essay, you can search for it. Essays that have been initially written in…