Thanks Aaron!



Auon

________________________________
From: Feng, Xixuan (Aaron) <[email protected]>
Sent: Thursday, March 2, 2017 6:18:53 PM
To: [email protected]
Subject: Re: Regarding new Perceptron module

Probably. You could refer to the SGD version of other modules, like SVM or
Logistic Regression.

- Aaron

2017年3月3日(金) 8:14 Kazmi,Auon H <[email protected]>:

> Hey Xixuan,
>
> I couldn't find your python and postgres files for MLP. Did you just work
> on C++ layer?
>
>
>
> Auon
>
> ________________________________
> From: Rahul Iyer <[email protected]>
> Sent: Wednesday, February 22, 2017 4:12:18 PM
> To: [email protected]
> Subject: Re: Regarding new Perceptron module
>
> I believe building a backprop-learned MLP would be much better than using
> the perceptron learning algo. In my experience, perceptron learning works
> quite slow; happy to hear other thoughts.
>
> On Wed, Feb 22, 2017 at 11:40 AM, Kazmi,Auon H <[email protected]> wrote:
>
> > Hi Xixuan,
> >
> > THanks! Is starting with single layer perceptron (and thus using
> > perceptron learning algo rather than SGD) a better idea?
> >
> >
> >
> > Auon
> >
> > ________________________________
> > From: Feng, Xixuan (Aaron) <[email protected]>
> > Sent: Tuesday, February 21, 2017 9:33:02 PM
> > To: [email protected]
> > Subject: Re: Regarding new Perceptron module
> >
> > Hi Auon,
> >
> > I have made some effort to try implementing multi-layer perceptron a few
> > years back but never got the time to finish it. Latest commits on these 2
> > branches has the history
> > https://github.com/haying/madlib/commits/nn_design
> > https://github.com/haying/madlib/commits/mlp
> >
> > I were using the convex programming framework in MADlib to implement it
> > with stochastic gradient descent. You may or may not do it in the same
> way.
> >
> > Thanks,
> > Feng, Xixuan (Aaron)
> >
> > On Wed, Feb 22, 2017 at 8:59 AM, Kazmi,Auon H <[email protected]> wrote:
> >
> > > Hi all,
> > >
> > > I am currently working on implementing Perceptron Learning Algorithm in
> > > Madlib. This module would serve the purpose of a single neuron when
> > > implementing any multi-layer neural network.
> > >
> > > Since, it involve state transitions, optimizations,etc.,  could you
> guys
> > > suggest a module that could help a little in this context?
> > >
> > >
> > >
> > >
> > >
> > >
> > > Regards,
> > >
> > > Auon
> > >
> >
> >
> >
> > --
> > - Aaron
> >
>
--
- Aaron

Reply via email to