Forum

The neural networks thing


#1

got this image in the feed a couple of days ago, then this article surfaced

made me think about the visual possibilities of the reverse pattern recognition that is drawing pixels

is there a conneciton to the recent machine learning pack ?
is there a connection to https://discourse.vvvv.org/t/12648 ?

any rants welcome


#2

that just blew my mind


#3

#4

wow, ggml… that’s cool. Is that of any use without programming knowledge? are there any tutorials? I’m just having a performance in my mind, where the AI produces images inspired by the actors…


#5


#6

what do i have to learn in order to that myself?


#7

http://googleresearch.blogspot.ru/2015/07/deepdream-code-example-for-visualizing.html


#8

#9

interesting introduction panel to deep learning


#10

captions from video


#11

clarifai boss on visualizing this structures https://www.youtube.com/watch?v=ghEmQSxT6tw


#12

this was in the shoutbox some months ago
neural talk and walk implementation

will this kind of library be compatible with the automatic importer from vl ?


#13

another one from kyle mcdonald’s feed

text prediction
examples http://rodarmor.com/artnet/
https://github.com/karpathy/char-rnn


#14

https://deepart.io/latest/


#15

for reference: this could be interesting to get started on the general topic: http://ml4a.github.io/


#16

One of the annoying things about machine learning at the moment is that the better known and documented frameworks tend to be built specifically for use with Linux (and to a lesser extent OSX). I came across an interesting discovery regarding Tensorflow models.

TFDeploy allows Python programmers to deploy their Tensorflow models using plain Numpy and Scikit. ^quote:TFDeploy:
Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.
^
For the training aspect of machine learning Tensorflow’s GPU accelerated libraries are really important, but Numpy should be fast enough to run fairly complex ML models.

It is possible to install Numpy and Scipy with Iron Python, and, as demonstrated by MicroD, Python code can be incorporated into vvvv. So is it possible that Tensorflow-trained models could be made to run inside vvvv?


#17

if i understand this correctly, you can also interface with gRTP to the running tensorflow application and going pure c# from there.

just an alternative


#18

#19

meanwhile there is also a .net binding for tensorflow: https://github.com/migueldeicaza/TensorFlowSharp


#20

any skillled person interested in slowly starting to bring this fidgets to the mmmmasses ?