neural networks

“So, one interesting thing is it's actually really, really easy to fit data. It's actually, it's quite boring. You know, you have, you know, a really large, complex model. Maybe it's a neural network. Maybe it's a random forest. Or maybe it's just a really larg…”

“Speech recognition, basically all the Siri processing or Android voice recognition is done with neural networks these days.”

“And you can see now, to even be competitive, you have to use neural networks.”

“These models work really well with labeled data. There are approaches where you can train without any labels but the performance is never as good as if you have well-labeled data.”

“When something can be done with a human created process then factually, oftentimes it's faster than a neural network.”

“All the technologies that we have today were developed around 50 years ago, plus minus a decade. Even deep learning that is so trendy today, it's basically very large neural networks. Concepts from the fifties matured around the seventies.”

“Every variable that you're trying to infer in a program should come with an uncertainty. Neural networks today are just, they're just a number in the neuron. It's like an activation level. But you need error bars around those numbers.”

“What took me two years along with a team to do, like, right now with the advances over the last few years in compute and in storage, you can do probably over a week.”

“That it's very like that in our lifetime, neural networks will become capable of learning anything and everything that we are capable of as humans.”

“Source code is one of the very few things that we generate with neural networks. That we can actually execute an introspect. It doesn't require human feedback to evaluate it. It doesn't require humans to step by step reason through it. We have built compilers,…”

“The way careers work is you want to be kind of novel, but if you're too novel, if you're too far out there, then your papers will get rejected, and that certainly happened to me a lot in the early days, like, 2010 of neural networks for natural language proces…”