ANN bypassing hidden layer for an input

Question

I have just been set an assignment to calculate some ANN outputs and write an ANN. Simple stuff, done it before, so I don't need any help with general ANN stuff. However, there is something that is puzzling me. In the assignment, the topology is as follows(wont upload the diagram as it is his intellectual property):-

2 layers, 3 hiddens and one output.
Input x1 goes to 2 hidden nodes and the output node.
Input x2 goes to 2 hidden nodes.

The problem is the ever so usual XOR. He has NOT mentioned anything about this kind of topology before, and I have definitely attended each lecture and listened intently. I am a good student like that :)

I don't think this counts as homework as I need no help with the actual tasks in hand.

Any insight as to why one would use a network with a topology like this would be brilliant.

Regards

score 3 · Accepted Answer · edited May 23 '17 at 12:13

3

enter image description here

Does the neural net look like the above picture? It looks like a common XOR topology with one hidden layer and a bias neuron. The bias neuron basically helps you shift the values of the activation function to the left or the right.

For more information on the role of the bias neuron, take a look at the following answers:

Update

I was able to find some literature about this. Apparently it is possible for an input to skip the hidden layer and go to the output layer. This is called a skip layer and is used to model traditional linear regression in a neural network. This page from the book Neural Network Modeling Using Sas Enterprise Miner describes the concept. This page from the same book goes into a little more detail about the concept as well.

edited May 23 '17 at 12:13

Community

1
1

answered Nov 01 '13 at 18:09

Vivin Paliath

94,126
40
223
295

Thank you for your answer. No, when I say that one of the inputs goes to the output node(weighted of course), I literally refer to one of the elements from the input vector. So in your example, lets say that A goes to the output node as well as H1. – Jack H Nov 01 '13 at 19:45
But not H2, lets say. – Jack H Nov 01 '13 at 19:45
Hmm that's a strange topology; I haven't seen that before but then again my level of experience with neural networks is at the amateur level. – Vivin Paliath Nov 01 '13 at 20:23
Well this is on an university introductory ANN course..... I thought it was really strange too. – Jack H Nov 01 '13 at 20:28
Incidentally, it makes the implementation very messy :/ – Jack H Nov 01 '13 at 20:29
Seems so. I wonder if there is any literature about this kind of implementation. – Vivin Paliath Nov 02 '13 at 17:00
I was able to find some literature about this concept. Hope this helps you out! – Vivin Paliath Nov 02 '13 at 18:40
1

Ah brilliant, that at least provides some explanation for it, and verifies that it is something that can actually be done! Very strange I must admit! – Jack H Nov 03 '13 at 11:36
Quite strange! I had never heard of this until I saw your question! – Vivin Paliath Nov 03 '13 at 20:38

ANN bypassing hidden layer for an input

1 Answers1