Editing 2173: Trained a Neural Net
Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.
The edit can be undone.
Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 8: | Line 8: | ||
==Explanation== | ==Explanation== | ||
− | This is | + | {{incomplete|Created by a TRAINED NEURAL NET. This is an incredibly stubby explanation; please expand. Do NOT delete this tag too soon.}} |
+ | An {{w|artificial neural network}}, or a neural net, is a computing system inspired by a human brain, which "learns" by considering lots and lots of examples to develop patterns. For example, these are used in image recognition - by analyzing thousands or millions of examples, the system is able to identify particular objects. Neural networks typically function with no prior knowledge, and are "trained" by feeding in examples of the thing that they are told to analyze. | ||
− | + | Here, [[Cueball]] is telling [[White Hat]] how he trained a neural net to sort photos into categories. The joke in the comic is that a human brain is already a neural network, albeit a biological one instead of an artificial one. By teaching oneself (or others) to do a task, you are ''de facto'' training a neural network. So instead of designing and training an artificial neural net that could do this task, all he did was manually sort the photos. | |
− | + | It is not advisable to say this in real life, because you might then be expected to use your already-trained neural net to do a similar task (or redo the same task) with much greater speed, thus ruining the façade. Also, people are offended when they are referred to by programers as deterministic automata with no free will. | |
− | + | [https://www.researchgate.net/profile/Diego_Moussallem/publication/326030040_Neural_Machine_Translation_for_Query_Construction_and_Composition Some contemporary neural nets have been trained to answer questions about the contents of Wikipedia.] You [http://chat.dbpedia.org try one] that [https://wiki.dbpedia.org/contribute you can also help train]. Technically, improving Wikipedia helps train it, but for example [https://github.com/dbpedia/GSoC/issues/11 you can also look for problems with the net's output.] | |
− | The title text is a continuation of this joke, as instead of designing and training two artificial neural nets named "Emily" and "Kevin", all he has done is train two people | + | The title text is a continuation of this joke, as instead of designing and training two artificial neural nets named "Emily" and "Kevin", all he has done is train two people to manually respond to support tickets. |
− | |||
− | |||
− | |||
− | |||
==Transcript== | ==Transcript== | ||
− | :[White Hat | + | :[Single panel with White Hat and Cueball, with White Hat holding what appears to be a smartphone.] |
:White Hat: Oh, hey, you organized our photo archive! | :White Hat: Oh, hey, you organized our photo archive! | ||
:Cueball: Yeah, I trained a neural net to sort the unlabeled photos into categories. | :Cueball: Yeah, I trained a neural net to sort the unlabeled photos into categories. | ||
Line 30: | Line 27: | ||
:[Caption below the panel:] | :[Caption below the panel:] | ||
:Engineering Tip: When you do a task by hand, you can technically say you trained a neural net to do it. | :Engineering Tip: When you do a task by hand, you can technically say you trained a neural net to do it. | ||
− | |||
− | |||
− | |||
{{comic discussion}} | {{comic discussion}} | ||
Line 38: | Line 32: | ||
[[Category:Comics featuring Cueball]] | [[Category:Comics featuring Cueball]] | ||
[[Category:Comics featuring White Hat]] | [[Category:Comics featuring White Hat]] | ||
− | |||
[[Category:Artificial Intelligence]] | [[Category:Artificial Intelligence]] |