Tags: neural

3

sparkline

Ways to think about machine learning — Benedict Evans

This strikes me as a sensible way of thinking about machine learning: it’s like when we got relational databases—suddenly we could do more, quicker, and easier …but it doesn’t require us to treat the technology like it’s magic.

An important parallel here is that though relational databases had economy of scale effects, there were limited network or ‘winner takes all’ effects. The database being used by company A doesn’t get better if company B buys the same database software from the same vendor: Safeway’s database doesn’t get better if Caterpillar buys the same one. Much the same actually applies to machine learning: machine learning is all about data, but data is highly specific to particular applications. More handwriting data will make a handwriting recognizer better, and more gas turbine data will make a system that predicts failures in gas turbines better, but the one doesn’t help with the other. Data isn’t fungible.

Turning Design Mockups Into Code With Deep Learning - FloydHub Blog

Training a neural network to do front-end development.

I didn’t understand any of this.

The Infinite Trad Session

Okay, this is kind of nuts: some researchers have seeded a neural network with all the tunes from The Session. Some of the results are surprisingly okay. It’s certainly a fascinating project.