zlacker

[parent] [thread] 3 comments
1. r0b05+(OP)[view] [source] 2020-05-14 08:12:26
If you're using a blacklist, it it really machine learning? Or are you using it to re-train?
replies(2): >>codegl+h5 >>Breza+kKa
2. codegl+h5[view] [source] 2020-05-14 08:55:45
>>r0b05+(OP)
blacklist is probably to avoid cases where it randomly generates a real word like above two cases, so that blacklist filter is probably applied after the ml stuff.
replies(1): >>turtle+y6
◧◩
3. turtle+y6[view] [source] [discussion] 2020-05-14 09:05:56
>>codegl+h5
Yup, the line for the blacklist lookup is here: https://github.com/turtlesoupy/this-word-does-not-exist/blob...
4. Breza+kKa[view] [source] 2020-05-18 03:51:28
>>r0b05+(OP)
Data scientist here. It's common to define boundaries for a machine learning algorithm by hand. Think of telling a chess AI that it can't move pieces off the board.
[go to top]