Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

SO I'm looking at these two neural networks and walking through how the ijk values of Theta correspond to the layer, the node number, and either there are redundant values or I'm missing how the subscripts actually map from node to node.

Theta^i_jk ... where this is read as " Theta superscript i subscript jk "

As shown here: example2

It looks like the Theta value corresponding to the node circled in teal would be Theta^2_12 ... where:

  • superscript i=2 ( layer 2 )
  • j=1 ( node number within the subsequent layer ? )
  • k=2 ( node number within the current layer ? )

If i'm matching the pattern correctly I think the j value is the node to the right of the red circled node ... and the k value is the teal node...

Am I getting this right?

Because between the above image and this one:


That seems to be the case ... can I get a confirmation on this?

share|improve this question

1 Answer 1

Yes, $\Theta^l_{ij}$ is the weight that the activation of node $i$ has in the previous input layer $l - 1$ in computing the activation of node $j$ in layer $l$.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.