Andrej Karpathy

It was basically a benchmark that allowed the deep learning community to demonstrate that deep neural networks actually work.

It was...

there's a massive value in that.

So I think ImageNet was useful, but basically it's become a bit of an MNIST at this point.

So MNIST is like little 28 by 28 grayscale digits.

There's kind of a joke data set that everyone like just crushes.

Yeah, I could see that being helpful, but not in sort of like mainline computer vision research anymore, of course.

I mean, you know, the error rates are...

Yeah, we're getting like 90% accuracy in 1,000 classification way prediction.

And I've seen those images and it's like really high.

That's really good.

If I remember correctly, the top five error rate is now like 1% or something.

Unfortunately, I don't think academics currently have the next ImageNet.

We've obviously... I think we've crushed MNIST.

We've basically kind of crushed ImageNet.

And there's no next sort of big benchmark that the entire community rallies behind and uses...

you know, for further development of these networks.

It was the right amount of difficult.

It was the right amount of difficult and simple and interesting enough.

It just kind of like, it was the right time for that kind of a data set.