I don't work with them, personally, but it's my understanding that if you want to use your own training set with Deep Learning, you basically need thousands of samples, and your own computing cluster.
RE: What Are Neural Networks, Why They Are So Popular And What Problems Can Solve
You are viewing a single comment's thread from:
What Are Neural Networks, Why They Are So Popular And What Problems Can Solve
It depends on the task, but basically you are right. Training stage requires a lot of computational power. If someone implements Deep Learning at Amazon servers, he probably spends few million dollars for just server infrastructure
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit
It does require "a lot" of computing power. But considering what leaps and bounds we've come in the last few years, you would be amazed at what you can do with a normal desktop PC or even a smartphone these days.
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit
yeah. Computers and processors are developed rapidly. Moreover there are some amazing parallelization technologies that can essentially alleviate computational requirements.
I think in a few years training of neural network will barely be a big problem.
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit