[Insight-users] Neural Network

Raghu Venkatram raghu.venkatram at gmail.com
Mon Aug 22 13:06:04 EDT 2005


Hi Stephanie,

Thanks for the input. We are working on a NeuralNetwork reader/writer,
to save state.
So that a network could be saved and loaded, or even modify network topology.
Thanks for adding the getweightset(). 

-Raghu

On 8/22/05, stephanie-powell-1 at uiowa.edu <stephanie-powell-1 at uiowa.edu> wrote:
> Hi,
> 
> I have tried implementing the ITK Neural Network code, and I think
> functionality needs to be added to get the resulting weights from the neural
> network (complimentary to AddWeightSet).  In my software, the neural net is
> trained for ~1 day and saved, then the net can be trained again at a later
> date.
> 
> I added the following code:
> /* MultilayerNeuralNetworkBase.h */
> WeightVectorType GetWeightSet();
> 
> /* MultilayerNeuralNetworkBase.txx */
> template<class TVector, class TOutput>
> typename MultilayerNeuralNetworkBase<TVector, TOutput>::WeightVectorType
> MultilayerNeuralNetworkBase<TVector,TOutput>
> ::GetWeightSet()
> {
>         return m_Weights;
> }
> 
> Thanks,
>   Stephanie
> 
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
>


More information about the Insight-users mailing list