MATLAB: Cascade-forward neural network adding new units

cascadecorrelation

For Cascade correlation network I found this definition: We add hidden units to the network one by one. Each new unit therefore adds a new one-unit "layer" to the network, unless some of its incoming weights happen to be zero. This is confuse me beacuse when I run Cascade network in MATLAB it looks like there is 10 neurons from beggining for example and I am not sure if it's the maximum of neurons only and it's really adding one by one during learning or there is 10 fixed neurons from beggining. How it works? Thank you.

Best Answer

As answered in your previous post.
Despite the name, these are different networks.
Hope this helps.
Greg
Related Question