Hi Stephanie<br>
<br>
<br>
<br>
<span class="q"><span class="gmail_quote">On 12/9/05, <b class="gmail_sendername">Stephanie Powell</b> <<a href="mailto:stephanie-powell-1@uiowa.edu" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">
stephanie-powell-1@uiowa.edu
</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div>Hi,</div>
<div> </div>
<div> I have implemented the OneHiddenLayerBackPropagationNeuralNetwork, but I have several questions about specific variables used in the NeuralNet class. </div>
<div> </div>
<div> Several of the variables & the use of these variables is unclear to me when using a three layer neural net. </div></blockquote><div><br>
</div><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div>
In the itkOneHiddenLayer... the user has the ability to set the
hidden and output layer bias (setting the bias) of the weight layers,
but it appears as though this variable is not used at all. There
is a variable called m_Bias that belongs to the BackPropagationLayer
class which is used (it's default value is 1), but the value itself is
never set. Why is the weights bias value adjusted when it's not
used and the layer bias value not adjusted when it is used in training?</div>
</blockquote></span>
<div> <br>
The weight corresponding to the bias value is adjusted. the bias itself
is not adjusted, so when you forward propagate, it is a constant value
of 1.0 or whatever you set it to using SetBias. But, yes, the bias in
the backpropagation layer should be set in the onehiddenlayernetwork,
instead of setting it in the weightset.<br>
</div>
<span class="q"><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div> </div>
</blockquote><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div>
Also, when training with momentum, it appears as though the
momentum is defaulted to 0.9, but there is no functionality allowing
the user to change this value. Was it assumed that the user would
not want to adjust this value as a training parameter?</div></blockquote></span>
<div><br>
<br>
thank you for pointing this out, I will commit the necessary fixes soon.<br>
The network IO is almost complete. I will email you the files ASAP.<br>
<br>
Your input is really valuable.<br>
<br>
As for the variables, we will soon have a chapter in the ITK Software guide, explaining all the variables in detail.<br>
<br>
Also please let me know if you would like any other functionality.<br>
<br>
Thanks,<br>
Raghu<br>
</div>
<br>
<br><br><div><span class="gmail_quote">On 12/9/05, <b class="gmail_sendername">Stephanie Powell</b> <<a href="mailto:stephanie-powell-1@uiowa.edu">stephanie-powell-1@uiowa.edu</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div>Hi,</div>
<div> </div>
<div> I have implemented the OneHiddenLayerBackPropagationNeuralNetwork, but I have several questions about specific variables used in the NeuralNet class. </div>
<div> </div>
<div> Several of the variables & the use of these variables is unclear to me when using a three layer neural net. <br>
<br>
In the itkOneHiddenLayer... the user has the ability to set the
hidden and output layer bias (setting the bias) of the weight layers,
but it appears as though this variable is not used at all. There
is a variable called m_Bias that belongs to the BackPropagationLayer
class which is used (it's default value is 1), but the value itself is
never set. Why is the weights bias value adjusted when it's not
used and the layer bias value not adjusted when it is used in training?
<br>
<br>
Also, when training with momentum, it appears as though the
momentum is defaulted to 0.9, but there is no functionality allowing
the user to change this value. Was it assumed that the user would
not want to adjust this value as a training parameter?<br>
<br>
Thanks,<br>
Stephanie<br>
</div>
<br>_______________________________________________<br>Insight-users mailing list<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:Insight-users@itk.org">Insight-users@itk.org</a><br><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">
http://www.itk.org/mailman/listinfo/insight-users</a><br><br><br></blockquote></div><br>