[Scilab-users] Gsoc 2018 toolbox in scilab

classic Classic list List threaded Threaded
4 messages Options
Amit Amit
Reply | Threaded
Open this post in threaded view
|

[Scilab-users] Gsoc 2018 toolbox in scilab

This post was updated on .
CONTENTS DELETED
The author has deleted this message.
Clément David-3 Clément David-3
Reply | Threaded
Open this post in threaded view
|

Re: Gsoc 2018 toolbox in scilab

Hello Amit,

It would be nice to have a machine learning however you could start by taking a look at what's
already exists in http://atoms.scilab.org and on http://scilab.io/category/machine-learning . Could
you try to improve what's already existing ?

Thanks,

--
Clément

Le vendredi 16 février 2018 à 04:57 -0700, amit2rockon a écrit :

> Hello everyone, Myself Amit Kumar, new to this community, I have completed
> machine learning course by Andrew Ng and completed my assignment with
> Matlab. I think I could have done with Scilab. I want to contribute to this
> organization and also want to participate in GSoC 2018. So can anybody here
> help me from where i can start? i want to implement machine learning
> functions in toolboxes.
>
>
>
> --
> Sent from: http://mailinglists.scilab.org/Scilab-users-Mailing-Lists-Archives-f2602246.html
> _______________________________________________
> users mailing list
> [hidden email]
> http://lists.scilab.org/mailman/listinfo/users
_______________________________________________
users mailing list
[hidden email]
http://lists.scilab.org/mailman/listinfo/users
Amit Amit
Reply | Threaded
Open this post in threaded view
|

Re: Gsoc 2018 toolbox in scilab

This post was updated on .
i checked https://wiki.scilab.org/Machine%20Learning%20Toolbox%20in%20Scilab
and improvement areas are mentioned in "Ideas/Direction To Work in Future" .
i would really like to work on it. How to proceed?



--
Sent from: http://mailinglists.scilab.org/Scilab-users-Mailing-Lists-Archives-f2602246.html
_______________________________________________
users mailing list
users@lists.scilab.org
http://lists.scilab.org/mailman/listinfo/users
Tan Chin Luh-2 Tan Chin Luh-2
Reply | Threaded
Open this post in threaded view
|

Re: Gsoc 2018 toolbox in scilab

In reply to this post by Clément David-3
Hi  Amit,

Greeting. I am Chin Luh, the author for Neural Network module in atoms
portal (https://atoms.scilab.org/toolboxes/neuralnetwork/2.0). Thlde
module is base on the book "Neural Network Design" by Hagan Martin (1st
version) and the codes are following the pseudo code given in the book.

If you are interested, you could look into this module and implement the
"Regularization" into the algorithms for all the FFBP  in the module,
which is highlighted in one of the session in Andrew Ng's  machine
learning course.

One thing you might need to be careful: In Machine Learning Course you
attended, Prof Andrew using the notation where the training dataset
arranged in rows, and the features arranged in columns. This is the
reverse with this module, the book this module referred to, as well as
the standard way python used. However, In Prof Andrew first course in
Deep Learning specialization, he used the same notation with this module.

As this module is totally in Scilab code, I personally believe that it
is easy to start.

Just my 2 cents, hope this helps.

Thanks.

Regards,
Chin Luh

On 16/2/2018 11:50 PM, Clément David wrote:

> Hello Amit,
>
> It would be nice to have a machine learning however you could start by taking a look at what's
> already exists in http://atoms.scilab.org and on http://scilab.io/category/machine-learning . Could
> you try to improve what's already existing ?
>
> Thanks,
>
> --
> Clément
>
> Le vendredi 16 février 2018 à 04:57 -0700, amit2rockon a écrit :
>> Hello everyone, Myself Amit Kumar, new to this community, I have completed
>> machine learning course by Andrew Ng and completed my assignment with
>> Matlab. I think I could have done with Scilab. I want to contribute to this
>> organization and also want to participate in GSoC 2018. So can anybody here
>> help me from where i can start? i want to implement machine learning
>> functions in toolboxes.
>>
>>
>>
>> --
>> Sent from: http://mailinglists.scilab.org/Scilab-users-Mailing-Lists-Archives-f2602246.html
>> _______________________________________________
>> users mailing list
>> [hidden email]
>> http://lists.scilab.org/mailman/listinfo/users
> _______________________________________________
> users mailing list
> [hidden email]
> http://lists.scilab.org/mailman/listinfo/users


_______________________________________________
users mailing list
[hidden email]
http://lists.scilab.org/mailman/listinfo/users