Hacker News Reader

What would happen if you generated a lot of images like this, tagged them as "conv-net filter", and then added them to the set of images that the neural nets trained on?

Would the network learn more discriminating filters for everything else?

View on HN

Very interesting question and worth an experiment or two. Personally, I don't think it would help because the patterns are complex and it is an internal representation. It would be like feeding it a hash values and labelling them "hash values". That wouldn't necessarily help you discriminate pre-hashed values. That said, I would definitely be interested in the results of a real test.

Reply on news.ycombinator.com