|
From: | Nicholas Jankowski |
Subject: | Re: Proceeding with the GSoC Project |
Date: | Thu, 26 Apr 2018 19:18:11 -0400 |
Due to ASCII encoding, something like this will happen... say we have 2 proper words, 'amuse' and 'abuse', and someone types in 'atuse'. In such a case, the network by default would output 'amuse' because ASCII of 't' is closer to 'm' than it is to 'b'. I did not considered this to be a problem because essentially the network really is giving us 'the closest match', however, even if we do consider this to be a problem, considering all the classes within a probability range instead of the class of highest probability would solve it.
[Prev in Thread] | Current Thread | [Next in Thread] |