0
$\begingroup$

Suppose the training data there exist an element of some data being misleading and some being right, how could the Neural network be trained so that it could filter the right data from the wrong one?

Excuse me if this question is written as a bit non technically my knowledge is not that high of this topic.

Improve this question
$\endgroup$
1
  • $\begingroup$ Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. $\endgroup$
    – Community Bot
    Commented Jul 25, 2022 at 0:37

1 Answer 1

Reset to default
1
$\begingroup$

For all intents and purposes, the neural networks are not protected against bias dataset unless the dataset is explicitly curated wrt to an arbitrary bias.

This is very much an open problem and a busy research area with many researchers attempting to address this problem in academic and production environments.

Some of the work on solving this is specific circumstances involves weighting certain data differently and utilizing statistical techniques to otherwise counteract the biases.

Improve this answer
$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .