In the neural network community, is a tensor pretty much always just a multi-dimensional array?
$\begingroup$
$\endgroup$
2
asked Nov 13, 2015 at 3:05
-
$\begingroup$ At least for Theano and TensorFlow this seems to be the case. $\endgroup$– Vladislavs DovgalecsNov 13, 2015 at 6:47
-
$\begingroup$ Yes, in the same sense that a matrix is just a 2 dimensional array. But tensors just simplify notation and programming just as matrix operation simplifies multivariate methods. In particular for a convolutional net, you have 1 image (tile) being processed by a bank of filters, which can be expressed as a single tensor operation. $\endgroup$– seanv507Nov 13, 2015 at 7:07
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Tensors in the neural network community = vector (1D-tensor), matrix/array (2D-tensor), or multi-dimensional array (nD-tensor, with $n > 2$).
Examples:
answered Sep 4, 2016 at 13:13