2
$\begingroup$

I read about time delay neural network (TDNN) and I am not sure I understood it. From what I read it seems that tdnn works just like one dimensional convolutional neural network (CNN).

What are the differences between the architectures, if they exist?

$\endgroup$

2 Answers 2

3
$\begingroup$

I found the answer - there is no difference.

According to the paper "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks": "Time Delay Neural Networks (TDNNs), also known as one dimensional Convolutional Neural Networks (1-d CNNs)..."

$\endgroup$
1
$\begingroup$

They are the same, as far as i can see. The name convolution usually applies to spatial not time dimensions, but that is only convention. Wikipedia also links the two.

$\endgroup$
1
  • 1
    $\begingroup$ In signal processing (e.g. audio or radio) convolution typically implies time dimension. $\endgroup$
    – kylefinn
    Jul 15, 2022 at 18:00

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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