Neural Networks
- Started
- Last post
- 46 Responses
- uan1
Music Transformer: Generating Music with Long-Term Structure
- drgs1
- drgs1
- drgs1
- inteliboy1
anyone done a music vid with this tech yet? only a matter of time.
- sofas-1
Building neural networks for fun/work is acceptable (many times encouraged) because we can hardly empathize with them and because many times we make humans for the same reasons, so it seems normal.
I'm not totally against it, but this practice isn't really criticised.
- They aren't people.monospaced
- Just fancy calculators.monospaced
- true (even though we're talking *extremely* fancy calculators). Still, we're heading towards beings having a consciousness on par if not higher than humanssofas
- That's debatable, and a well documented concept.monospaced
- yup.
also sorry for this coming out quite provocative.sofas - No apologies necessary.monospaced
- drgs1
- drgs1
- drgs0
It all works very superficially for now, it rearranges the fragments from one style reference image to recreate the content image
Ideally it the network should be trained on all works from the same painter, but for this you need to learn association between the actual real image and how the artist saw and painted it, which is something completely different
- drgs1
- scarabin0
i was so struck by this stuff i had a dream about it last night. i had taken a picasso line drawing and combined it with a picasso painting to come up with an "original" picasso that i used legally in a layout i was working on.
- uan0
DeepSpeech
Mozilla’s Open Source Speech Recognition Model and Voice Datasethttps://github.com/mozilla/DeepS…
Project DeepSpeech is an open source Speech-To-Text engine. It uses a model trained by machine learning techniques, based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow project to make the implementation easier.
- drgs0
- monospaced0
Perhaps this is how the Prisma app/service works. Fascinating.
- uan0