Comments on: Summer of Synapse http://blog.peltarion.com/2008/07/02/summer-drive/ The Peltarion Blog Fri, 21 Nov 2008 07:17:09 +0000 http://wordpress.org/?v=2.6.2 By: Luka (Peltarion) http://blog.peltarion.com/2008/07/02/summer-drive/#comment-20819 Luka (Peltarion) Fri, 08 Aug 2008 03:33:55 +0000 http://blog.peltarion.com/?p=71#comment-20819 Synapse uses a component based approach which for a NN means that the weights and the non-linear function are separated into two blocks, the weight layer and the function layer. Bias weights are on the function layer. The weight layer is a simple inputs x outputs matrix. For more information see: http://www.peltarion.com/doc/index.php?title=Synapse:Function_layer_block http://www.peltarion.com/doc/index.php?title=Synapse:Weight_layer_block If you have any more questions, please email us at info(AT)peltarion.com Synapse uses a component based approach which for a NN means that the weights and the non-linear function are separated into two blocks, the weight layer and the function layer. Bias weights are on the function layer. The weight layer is a simple inputs x outputs matrix.

For more information see:
http://www.peltarion.com/doc/index.php?title=Synapse:Function_layer_block

http://www.peltarion.com/doc/index.php?title=Synapse:Weight_layer_block

If you have any more questions, please email us at info(AT)peltarion.com

]]> By: Sandhya Samarasinghe http://blog.peltarion.com/2008/07/02/summer-drive/#comment-20756 Sandhya Samarasinghe Thu, 07 Aug 2008 02:53:38 +0000 http://blog.peltarion.com/?p=71#comment-20756 Hi I am using Peltarion for my NN postgraduate class. I wanted my students to do a small 2-d classfication using a linear neuron and extract the weights from Synapse and then draw classification boundary on the data. It seems that Synapse does not use bias weights carrying an input of +1 that allows intercept. In Synapse, weights seems to be associated with only the disignated inputs. When I extract these and draw the classification boundary on the data, it does not produce the correct bundary that should divide the data into two regions. Other NN software that I use have bias weight and I get the correct classification boundary from it. Can you please tell me the structure of weights in Synapse? Hi
I am using Peltarion for my NN postgraduate class. I wanted my students to do a small 2-d classfication using a linear neuron and extract the weights from Synapse and then draw classification boundary on the data. It seems that Synapse does not use bias weights carrying an input of +1 that allows intercept. In Synapse, weights seems to be associated with only the disignated inputs. When I extract these and draw the classification boundary on the data, it does not produce the correct bundary that should divide the data into two regions. Other NN software that I use have bias weight and I get the correct classification boundary from it. Can you please tell me the structure of weights in Synapse?

]]>