Talk:Concept learning

Wiki Education Foundation-supported course assignment

This article was the subject of a Wiki Education Foundation-supported course assignment, between 8 January 2020 and 25 April 2020. Further details are available on the course page. Student editor(s): Kkrussell97.

Above undated message substituted from Template:Dashboard.wikiedu.org assignment by PrimeBOT (talk) 18:16, 16 January 2022 (UTC)

Untitled

Article is fantasy and not based on any real research — Preceding unsigned comment added by 68.187.203.232 (talk) 22:40, 9 November 2019 (UTC)

WikiProject Robotics

^ why is this a part of robotics? The article itself states this is a psychology / cognitive learning theory article. — Preceding unsigned comment added by 199.27.109.101 (talk • contribs)

Removed from the WikiProject. I'll remove the section on machine learning as well, it's pretty incoherent. QVVERTYVS (hm?) 20:53, 1 May 2015 (UTC)

Very sketchy article

I notice the "need for an expert" post. I'm not a psychology expert but I know a bit about machine learning. This article is riddled with nonsensical phrases about machine learning, math, etc. It feels a lot like what you'd expect of a student essay submission (which I see below may have been the case) that acts as an authority but really is a gibberish combination of words. For example:

> Neural networks are based on computational models of learning using factor analysis or convolution.

Neither factor analysis not convolution is a learning algorithm for neural networks (though someone somewhere has probably applied factor analysis in some way). It doesn't even make sense to speak of convolution as a learning algorithm. Convolutional neural networks exist (one of many NN configurations), but "convolution" in this context describes neural network graph connectivity and weight sharing, and has little effect on the learning algorithm. Even giving this statement the benefit of the doubt, it makes no sense to bring up convolutional neural networks when speaking of neural network learning in general.

And some more:

> In the machine learning literature, this concept learning is more typically called supervised learning or supervised classification, in contrast to unsupervised learning or unsupervised classification, in which the learner is not provided with class labels.

This is totally and completely wrong, and contradicts the article itself. Both unsupervised and supervised learning can be thought of as concept learning. The article itself says this:

> Examples - Supervised or unsupervised generalizing from examples may lead to learning a new concept, but concept formation is more than generalizing from examples.

To actually address the topic: In machine learning, the closest term to "concept learning" would be "representation learning".

Honestly there are so many sketchy parts of this essay I can't count them all and would take me too long to point them all out. The article is so all over the place and vague and undirected, I don't even know what it's trying to get at. It feels more like an explosion of various ideas from disparate sources (machine learning, psychology) splatted onto a page with no organization and with the author having no particular understanding of either topic (at least certainly not machine learning).

Bottom line is this article has so many inaccuracies (based on what I know about machine learning), I can't trust anything it says about what I don't know well (psychology). In my opinion the whole article is useless because of this, and should be removed and/or rewritten. — Preceding unsigned comment added by 199.27.109.101 (talk) 02:39, 26 March 2014 (UTC)

Note on contributions to this article

Work on this page is being conducted as a group project of Dr. Kent Norman's Fall semester 2007 course, Thinking and Problem Solving, at the University of Maryland, College Park.

Klnorman 02:08, 15 November 2007 (UTC)

Comments

A group from the University of Maryland taking Psychology of Thinking and Problem Solving will be editing this page throughout the rest of the semester. If editors could refrain from changing the article until after the 10th of December, it would be greatly appreciated. —Preceding unsigned comment added by Lucgoose11 (talk • contribs) 16:12, 19 November 2007 (UTC)

Really happy to hear it! Look forward to seeing your work. —Dfass (talk) 13:07, 10 December 2007 (UTC)

Types of Concept

So is the "Types of Concept" section just subtitles with bits missing? What a mess. I may add some more info and citing but I'm not an expert.

There's also a ton of broken referencing in this article. --Furbybrain (talk) 13:18, 25 January 2018 (UTC)

Fixing referencing

ok so I'm going to try and fix the referencing on this article... Apologies if I make it worse before I make it better --Furbybrain (talk) 01:08, 18 January 2019 (UTC)

I had to go back to this version to work out what was going on with the random number which didn't seem to reference anything — Preceding unsigned comment added by Furbybrain (talk • contribs) 01:29, 18 January 2019 (UTC)

The Meaning of NTS

In its current version, in the fist paragraph of this article is the string of characters "NTS." Will somebody please explain what does it mean? Thomas Foxcroft (talk) 18:37, 24 September 2019 (UTC)

Citation and Scope of Article

Hello All! My two comments about this article are that the source goes between psychological perspective of learning to machine learning. These topics are distinct, so a new article for ML and this theory and framework should be made if that is an important and original article to feature. It detracts from the purpose and makes the article confusing.

Sources need to be updated as well. Much of this information seems to be based upon opinion and perspective, not sourced information.

Best Colin Saideman (talk) 04:00, 9 August 2022 (UTC)