Talk:Machine learning

Show us some successes!

This entire article is about theory with no demonstrated path or evidence to success/usefulness. I was exposed to Neural Net promises over 20 years ago. Show us some results, or at least declare there is nothing to report.--2600:6C48:7006:200:5C10:C716:750B:C3B2 (talk) 00:25, 17 September 2024 (UTC)

Machine learning is also present in modern day mining

Machine learning and deep learning have increasingly attracted interest over the last five years and we often see these terms applied in the context of mineral exploration, mine exploitation and geoscience studies.

I recommend adding mining as another Application to machine learning. In the mining industry, both recent start-up companies and well-established mining and service companies are implementing machine learning in all facets of their work. A structural geologist at the mining company I work at, SRK Consulting, wrote a published paper on this and presented it at the Geological Association of Canada in 2019.

References

Wiki Education assignment: Linguistics in the Digital Age

This article was the subject of a Wiki Education Foundation-supported course assignment, between 15 January 2024 and 8 May 2024. Further details are available on the course page. Student editor(s): Beachvolleyball101 (article contribs).

— Assignment last updated by Markovya (talk) 18:52, 20 March 2024 (UTC)

Wiki Education assignment: Research Process and Methodology - SP24 - Sect 201 - Thu

This article was the subject of a Wiki Education Foundation-supported course assignment, between 4 March 2024 and 4 May 2024. Further details are available on the course page. Student editor(s): Xc1181 (article contribs).

— Assignment last updated by Xc1181 (talk) 20:52, 21 April 2024 (UTC)

Definition "generalize to unseen data" is wrong

The definition of ML being to "generalize to unseen data" is incorrect, as it is slightly too narrow.

Machine Learning can be used to learn, example, how to play checkers without having to memoryze all possible checker states. An «easy» checkers agent could rely merely on a list of all possible game states and a corresponding recommended action. A ML algorithm could learn to condense those «all possible game states» into a concise set of rules.

Another example, clustering algorithms can be used merely for the purpose of clustering and without any intent of being applicable to "unseen data". The training of the clustering algorithm is still called "machine learning" and the clustering algorithms themselves are also still called "machine learning algorithms". 109.49.139.107 (talk) 17:15, 17 December 2024 (UTC)