Dr. Mark Humphrys

School of Computing. Dublin City University.

Home      Blog      Teaching      Research      Contact

My big idea: Ancient Brain

Search:

CA114      CA170

CA668      CA669      Projects

Neural Net Exercise - Binary Encoder Network

4 input nodes, 2 hidden, 4 output.
Exemplars:

Input 1 0 0 0  Output 1 0 0 0
Input 0 1 0 0  Output 0 1 0 0
Input 0 0 1 0  Output 0 0 1 0
Input 0 0 0 1  Output 0 0 0 1
i.e. We simply want it to represent these 4 inputs somehow in just 2 hidden nodes.

Make the hidden nodes produce simply 0 or 1 output. Then Question:
After training: For each exemplar, what do the 2 hidden outputs yj look like?


ancientbrain.com      w2mind.org      humphrysfamilytree.com

On the Internet since 1987.

Wikipedia: Sometimes I link to Wikipedia. I have written something In defence of Wikipedia. It is often a useful starting point but you cannot trust it. Linking to it is like linking to a Google search. A starting point, not a destination. I automatically highlight in red all links to Wikipedia and Google search and other possibly-unreliable user-generated content.