neural resonator..any help?

May 8, 2008 at 6:54am

neural resonator..any help?

Hi all, what do you think of this device..

http://www.jomox.de/upload/manuals/Resonator%20Neuronium%20ManualEng.pdf

i’m about to try to build something similar in max..is there anyone else who did something like this?

michele

#37627
May 8, 2008 at 7:20am
#130112
May 8, 2008 at 4:40pm

This is something I have been interested in for quite some
time. Using neural nets in Max that is…

A neural network is a network of weighting (learning)
functions that have a persistent weighted state. The weighting
function determines what impulses will pass through. When you
start out, your neural net is a blank slate. You have to feed
it data in order to train it.

This article suggests you can train the neural net with audio
feedback which is a very interesting concept. What is not clear
is what the learning function would be used. If the function just
pass the value through, you are not really “learning” anything.
I would be interested to know more about how different learning
functions could be applied and how that would change the flow of
data in the diagram (pic 9). His suggestion of using genetic
algorithms is interesting, but not really “learning”.

I think there are all sorts of interesting things you could
explore with neural nets. As far as I know there are no Max
externals out there that implement a neural net. Please let me
know if there is because that would save me a lot of time.
If anybody knows of a good general purpose neural net library,
I would definitely port it.

#130113
May 8, 2008 at 4:52pm

I think CNMAT made an external, but I cant seem to find it right now. I remember having it and not knowing what the heck to do with it. Ive seen others as well, at least one other.

http://www.maxobjects.com/?PHPSESSID=d7068802cc3c611d8ee0ec937c1f3147&PHPSESSID=d7068802cc3c611d8ee0ec937c1f3147&request=neural&operateur=AND&id_plateforme=0&Submit=OK

heres my search on maxobjects.com looks like there’s several. Id love to see a patch made with one that I could study.

#130114
May 8, 2008 at 4:57pm

Anthony Palomba wrote:
> His suggestion of using genetic
> algorithms is interesting, but not really “learning”.

GAs have been used with neural nets as ways of ‘evolving’ optimal
network topologies for various problems, which, AFAIK, correlates with
what we know about learning in the cognitive, embodied sense (that
brains aren’t fixed networks of nodes).

I didn’t read the blurb fully yet, but didn’t get much of a neural net
flavour (in the sense of learning structures) so much as a Gordon
Mumma’s cybernetic console kind of vibe. All very interesting …


Owen

#130115
May 8, 2008 at 7:21pm

hi Anthony,
i know a bunch of max objects-patches that deal with something similar but i’ve never been able getting something (to be honest i did not even understand some of these!)..

http://www.olliebown.com/main_blog/?page_id=8

http://www.neuromuse.org/downloads/index.html

best
mic

Quote: Anthony Palomba wrote on Thu, 08 May 2008 18:40
—————————————————-
> This is something I have been interested in for quite some
> time. Using neural nets in Max that is…
>
> A neural network is a network of weighting (learning)
> functions that have a persistent weighted state. The weighting
> function determines what impulses will pass through. When you
> start out, your neural net is a blank slate. You have to feed
> it data in order to train it.
>
> This article suggests you can train the neural net with audio
> feedback which is a very interesting concept. What is not clear
> is what the learning function would be used. If the function just
> pass the value through, you are not really “learning” anything.
> I would be interested to know more about how different learning
> functions could be applied and how that would change the flow of
> data in the diagram (pic 9). His suggestion of using genetic
> algorithms is interesting, but not really “learning”.
>
> I think there are all sorts of interesting things you could
> explore with neural nets. As far as I know there are no Max
> externals out there that implement a neural net. Please let me
> know if there is because that would save me a lot of time.
> If anybody knows of a good general purpose neural net library,
> I would definitely port it.
>
>
—————————————————-

#130116
May 8, 2008 at 8:06pm

hmmmm, very interesting. I will check it out.

#130117
May 8, 2008 at 11:28pm

Quote: Axiom-Crux wrote on Thu, 08 May 2008 09:52
—————————————————-
> I think CNMAT made an external, but I cant seem to find it right now.

Here’s our funny webpage about that:

http://archive.cnmat.berkeley.edu/MAX/neural-net.html

This project is dead.

mz

#130118
May 9, 2008 at 12:44am

Too bad there is only a mac version…

#130119
May 9, 2008 at 9:53am

I have an mxj Java class at:

http://miajo.co.uk/?MaxMSP:mxj_nnLists

… though I haven’t had time to check it with Max 5 (I know there are some mxj issues as someone reported my mxj curve~ not working).

Works in Max 4.6.3 though, and I’ll get round to it soon.

For info: This is about 4x slower than a C version by my calculations (the Java code was ported from some of my neural net C code using a similar algorithm).

#130120
May 9, 2008 at 9:56am

…Oh, and there is a FANN (Fast Artificial Neural Network Library) implementation if you search maxobjects.com

#130121
May 9, 2008 at 10:12am

Quote: martinrobinson wrote on Fri, 09 May 2008 11:56
—————————————————-
> …Oh, and there is a FANN (Fast Artificial Neural Network Library) implementation if you search maxobjects.com
—————————————————-

yes you are right, there is also olivier pasquet fann objects, but as above i can’t get anything interesting out of them maybe it’s my fault!

http://www.opasquet.fr/?page_id=8

#130122
May 9, 2008 at 3:21pm

again, only for mac. :(

#130123
May 12, 2008 at 2:26am

The Hartmann Neuron was based on a traditional net:
http://www.hartmann-music.com/home/us/news/
If I recall correctly, the company went bust and the software is
open-source now.

On Thu, May 8, 2008 at 12:40 PM, Anthony Palomba wrote:
>
> This is something I have been interested in for quite some
> time. Using neural nets in Max that is…
>
> A neural network is a network of weighting (learning)
> functions that have a persistent weighted state. The weighting
> function determines what impulses will pass through. When you
> start out, your neural net is a blank slate. You have to feed
> it data in order to train it.
>
> This article suggests you can train the neural net with audio
> feedback which is a very interesting concept. What is not clear
> is what the learning function would be used. If the function just
> pass the value through, you are not really “learning” anything.
> I would be interested to know more about how different learning
> functions could be applied and how that would change the flow of
> data in the diagram (pic 9). His suggestion of using genetic
> algorithms is interesting, but not really “learning”.
>
> I think there are all sorts of interesting things you could
> explore with neural nets. As far as I know there are no Max
> externals out there that implement a neural net. Please let me
> know if there is because that would save me a lot of time.
> If anybody knows of a good general purpose neural net library,
> I would definitely port it.
>
>
>
>
>


Morgan Sutherland

#130124
May 12, 2008 at 4:10pm

A google search did not turn up any links to an
open source Hartmann Neuron project. Do you have
any specific links?

A search of sourceforge did turn up a good number
of related projects…

http://sourceforge.net/search/?words=neuron&type_of_search=soft&pmode=0&words=neural&Search=Search

Could be some interesting things there.

#130125
May 13, 2008 at 10:59am

Hi Martin, thanks a lot for sharing your java obj..it seems really interensting and maybe this time i could fine my way through neaural-net..do you have any example patch, practical music implementation i can get inspiration/ideas from?..
how do you use it?
all the best

Quote: martinrobinson wrote on Fri, 09 May 2008 11:53
—————————————————-
> I have an mxj Java class at:
>
> http://miajo.co.uk/?MaxMSP:mxj_nnLists
>
> … though I haven’t had time to check it with Max 5 (I know there are some mxj issues as someone reported my mxj curve~ not working).
>
> Works in Max 4.6.3 though, and I’ll get round to it soon.
>
> For info: This is about 4x slower than a C version by my calculations (the Java code was ported from some of my neural net C code using a similar algorithm).
—————————————————-

#130126
May 15, 2008 at 11:44pm

Do anyone have an idea on how to implement Ashby Homeostat in Max ?

http://www.hrat.btinternet.co.uk/Homeostat.html

Page 15 = http://www.ecila.org/ecila_files/content/papers/ACEMScThesis.pdf

I tried some things… but nothing really working.

#130127
May 16, 2008 at 6:11am

Bertrand Fraysse schrieb:
> Do anyone have an idea on how to implement Ashby Homeostat in Max ?
>
> I tried some things… but nothing really working.

Look at the multislider help file, there is an eeg like example…


Stefan Tiedje————x——-
–_____———–|————–
–(_|_ —-|—–|—–()——-
– _|_)—-|—–()————–
———-()——–www.ccmix.com

#130128

You must be logged in to reply to this topic.