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 31: | Line 31: | ||
: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. | ||
β | ==Trivia== | + | ==Trivia==<!-- I continue to maintain that the following is a legitimate part of the explanation. ~~~~ --> |
β | *Cueball is depicted abusing the training of such a chatbot in [[1696: AI Research]]. | + | *[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 can [https://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.] | ||
+ | **Cueball is depicted abusing the training of such a chatbot in [[1696: AI Research]]. | ||
{{comic discussion}} | {{comic discussion}} |