Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> the problem won't be solved by collecting even larger datasets and using more GPUs, because leopard print sofas are inevitable.

The models have room for improvement, but it's not clear to me that larger datasets won't solve the problem. Larger datasets and more processing power is exactly why neural nets have surged in effectiveness recently. Who knows how much further current models can go with more data and processing power?



read the Hinton paper cited in the OP -- no amount of processing power will make CNNs represent structured latent variables




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: