Hacker News Reader

Your comment reminds me of this xkcd cartoon: https://xkcd.com/1425/

It's 5 years old now (coincidentally the time span quoted to develop a solution), but recognizing a bird was already considered a solved problem 3 years ago, less than 2 years after the publication of the cartoon.

Predicting the future is hard.

View on HN

Surprisingly, recognizing a bird is much harder when you count rare species and running birds. Thus, sparse data. Does it recognize penguins too?

AIs today still fail at it. Some folks were trying to train one to match endangered species and they had to pull mighty tricks to have some 70% accuracy. I think it was here on HN some time ago, but can't recall a link.

And yet, average humans can classify even fewer species.

Also after extensively studying ornithology?

With the same amount of training/data as NNs? I doubt it...

Do you take into account billions of years of training due to evolution?

Technically that’s network architecture, not training data... admittedly though humans are “pre-trained” from birth.

Reply on news.ycombinator.com