Summer of Synapse
Summer is here and Peltarion would like for you to enjoy it as much as we do. Therefore we are currently offering a limited number of Synapse Licenses at half price during July and August! The first licenses each month are automatically sold at half price. There is only a limited number though, so act while there is still time.
Are there discounted licenses left for this month? Visit our web shop and see for yourself!
Update: All discounted licenses have now been sold out. Congratulations to everyone that got a discounted license!
Entries (RSS)
August 7th, 2008 at 4:53
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?
August 8th, 2008 at 5:33
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