now work all good with last version of polymaththanks :-)2017-04-27 17:29 GMT+02:00 Oleks <[hidden email]>:OleksSorry for the delayHello,I have finally added a configuration to the NeuralNetwork project. Now you can use this Metacello script to load it into your Pharo image:
Metacello new
�� repository: 'http://smalltalkhub.com/mc/Oleks/NeuralNetwork/main ';
�� configuration: 'MLNeuralNetwork';
�� version: #development;
�� load.On Tue, Apr 25, 2017 at 4:13 PM, francescoagati [via Smalltalk] <[hidden email]> wrote:thanks ;-)2017-04-25 15:09 GMT+02:00 Oleks <[hidden email]>:Hello,There isn't one yet. But I will try to create it today. I will let you knowCheers,OleksOn Apr 25, 2017 16:10, "francescoagati [via Smalltalk]" <[hidden email]> wrote:Hi��Oleks,there is a mode for install neural network from metacello?2017-04-25 13:00 GMT+02:00 Alexandre Bergel <[hidden email]>:Continue to push that topic Oleks. You are on the right track!
Alexandre
--
> On Apr 24, 2017, at 1:43 AM, Oleks <[hidden email]> wrote:
>
> Hello,
>
> Thanks a lot for your advice! It was very helpful and educating (for
> example, I thought that we store biases in the weight matrix and prepend 1
> to input to make it faster, but now I see why it's actually slower that
> way).
>
> I've implemented a multi-layer neural network as a linked list of layers
> that propagate the input and error from one to another, similar to the Chain
> of Responsibility pattern. Also, now I represent biases as separate vectors.
> The LearningAlgorithm is a separate class with Backpropagation as its
> subclass (though at this point the network can only learn through
> backpropagation, but I'm planning to change that). I'm trying to figure out
> how the activation and cost functions should be connected. For example,
> cross-entropy works best with logistic sigmoid activation etc. I would like
> to give the user a freedom to use whatever he wants (plug in whatever you
> like and see what happens), but it can be very inefficient (because some
> time-consuming parts of activation and cost derivatives cancel out each
> other).
>
> Also, there is an interface for setting the learning rate for the whole
> network, which can be used to choose the learning rate prior to learning, as
> well as to change the learning rate after each iteration. I am planning to
> implement some optimization algorithms that would automize the process of
> choosing a learning rate (adagrad for example), but this would require a bit
> different design (maybe I will implement the Optimizer, as you suggested).
>
> I'm attaching two images with UML diagrams, describing my current
> implementation. Could you please tell me what you think about this design?
> The first image is a class diagram that shows the whole architecture, and
> the second one is a sequence diagram of backpropagation.
>
> mlnn.png <http://forum.world.st/file/n4943698/mlnn.png >
> backprop.png <http://forum.world.st/file/n4943698/backprop.png >
>
> Sincerely yours,
> Oleksandr
>
>
>
> --
> View this message in context: http://forum.world.st/Neural-Networks-in-Pharo-tp4941271p494 3698.html
> Sent from the Pharo Smalltalk Users mailing list archive at Nabble.com.
>
_,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:
Alexandre Bergel�� http://www.bergel.eu
^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;.
If you reply to this email, your message will be added to the discussion below:http://forum.world.st/Neural-Networks-in-Pharo-tp4941271p494 4025.html
View this message in context: Re: Neural Networks in Pharo
http://forum.world.st/Neural-NIf you reply to this email, your message will be added to the discussion below:etworks-in-Pharo-tp4941271p494 4028.html
View this message in context: Re: Neural Networks in Pharo
Sent from the Pharo Smalltalk Users mailing list archive at Nabble.com.
http://forum.world.st/Neural-If you reply to this email, your message will be added to the discussion below:Networks-in-Pharo- tp4941271p4944863.html