That works only for cats vs. dogs toy classifiers.
It had never ever worked for anything practical.
And no, Deep Learning is high science. It is not just throwing piles of data to PyTorch and run it on a 8-GPU cluster.
I don't blame anyone having this view. Megacorps with billions of bucks are in a race to train the biggest language models, and that is the news every media focuses on.
In this sense computers and language, for example, are also not a property of natural world. So you can't have sciences that study and/or use computers or languages?
It had never ever worked for anything practical.
And no, Deep Learning is high science. It is not just throwing piles of data to PyTorch and run it on a 8-GPU cluster.
I don't blame anyone having this view. Megacorps with billions of bucks are in a race to train the biggest language models, and that is the news every media focuses on.