Leaf – Machine Learning for Hackers

Re:Leaf – Machine Learning for Hackers by rrggrr on Monday April 25, 2016 @09:17AM (#11563955)

This is not the simplified abstraction I'm looking for. Give me an ML library that exposes the API using metaphors I can understand a relate to and I'm all over it. Leaf is still using terms and concepts I don't understand.

[ Parent | on HN ]

Re:Leaf – Machine Learning for Hackers by mjhirn on Monday April 25, 2016 @10:10AM (#11564272)

We think it is more beneficial for collaboration if we stick to the common naming of layers, functions and concepts than using metaphors. We provided two links, which help to get you started with that.

But with Leaf it becomes very easy to create modules (Rust crates) that expose layers/networks/concepts, which can have a metaphorical name.

[ Parent | on HN ]

Re:Leaf – Machine Learning for Hackers by philtar on Monday April 25, 2016 @09:33AM (#11564039)

Why stop there? Let's make it program itself and do whatever you want it to do just by looking at it.

[ Parent | on HN ]