[ml] Deep Learning ?

[Mike Schachter]

Sounds good, maybe we could meet up some time in August and
start putting something together. In the meantime I'll look into packages
we could use to train deep nets, either deep belief nets or stacked
auto-encoders or both. PyBrain claims to have support for deep nets:

http://pybrain.org/docs/

However, any neural network library should have support for deep nets,
because the pre-training just involves training layers of auto-encoders,
and each auto-encoder is just a normal neural network that has been
trained to reproduce it's input, with the output layer removed.

  mike


On Fri, Jul 22, 2011 at 11:26 AM, Ron Shigeta <rtshigeta at yahoo.com> wrote:
> I'm just starting to work with ML packages and have read a couple of deep
> learning papers, but would love to see some examples.  if it just turns into
> a working session with some basic data we've done i'd definitely show up for
> that too.
>
>
> ________________________________
> From: Mike Schachter <mike at mindmech.com>
> To: Ron Shigeta <rtshigeta at yahoo.com>
> Cc: "ml at lists.noisebridge.net" <ml at lists.noisebridge.net>
> Sent: Thursday, July 21, 2011 10:07 PM
> Subject: Re: [ml] Deep Learning ?
>
> Hi Ron,
>
> Yes, quite ambiguous! I'm down for a deep net meetup,
> maybe even a workshop, but haven't put together any
> of the materials and haven't used them for anything yet.
>
> Have you? Anyone else? I've heard of theano for using
> them but don't know of any formal frameworks that do
> the pre-training. I guess for a workshop or meetup we
> could just get an arbitrary neural net package and train
> layers of auto-encoders then stack them up? Any ideas?
>
>   mike
>
> On Thu, Jul 21, 2011 at 4:11 PM, Ron Shigeta <rtshigeta at yahoo.com> wrote:
>> Is there going to be a deep networks session at noisebridge in august?
>> would really like to come...but the calendar was ambiguous - at least the
>> part I read
>>
>> _______________________________________________
>> ml mailing list
>> ml at lists.noisebridge.net
>> https://www.noisebridge.net/mailman/listinfo/ml
>>
>>
>
>
>