Editing Minimum description length (section)

==Recent work on algorithmic MDL learning==

Recent machine MDL learning of algorithmic, as opposed to statistical, data models have received increasing attention with increasing availability of data, computation resources and theoretic advances.<ref>{{cite journal |last1=Zenil |first1=Hector |last2=Kiani |first2=Narsis A. |last3=Zea |first3=Allan A. |last4=Tegnér |first4=Jesper |title=Causal deconvolution by algorithmic generative models |journal=Nature Machine Intelligence |date=January 2019 |volume=1 |issue=1 |pages=58–66 |doi=10.1038/s42256-018-0005-0 |hdl=10754/630919 |s2cid=86562557 |hdl-access=free }}</ref><ref>{{cite journal |title=Remodelling machine learning: An AI that thinks like a scientist |journal=Nature Machine Intelligence |date=28 January 2019 |pages=1 |doi=10.1038/s42256-019-0026-3 |s2cid=189929110 }}</ref> Approaches are informed by the burgeoning field of [[artificial general intelligence]].  Shortly before his death, [[Marvin Minsky]] came out strongly in favor of this line of research, saying:<ref>Archived at [https://ghostarchive.org/varchive/youtube/20211205/DfY-DRsE86s Ghostarchive]{{cbignore}} and the [https://web.archive.org/web/20151226130036/https://www.youtube.com/watch?v=DfY-DRsE86s Wayback Machine]{{cbignore}}: {{cite web| url = https://www.youtube.com/watch?v=DfY-DRsE86s&feature=youtu.be&t=5402| title = The Limits of Understanding | website=[[YouTube]]| date = 14 December 2014 }}{{cbignore}}</ref>

{{quote|It seems to me that the most important discovery since Gödel was the discovery by Chaitin, Solomonoff and Kolmogorov of the concept called Algorithmic Probability which is a fundamental new theory of how to make predictions given a collection of experiences and this is a beautiful theory, everybody should learn it, but it’s got one problem, that is, that you cannot actually calculate what this theory predicts because it is too hard, it requires an infinite amount of work. However, it should be possible to make practical approximations to the Chaitin, Kolmogorov, Solomonoff theory that would make better predictions than anything we have today. Everybody should learn all about that and spend the rest of their lives working on it.|
Panel discussion on The Limits of Understanding, World Science Festival, NYC, Dec 14, 2014
}}