In the neural network community, is a tensor pretty much always just a multi-dimensional array?
Asked
Active
Viewed 1,276 times
7
-
At least for Theano and TensorFlow this seems to be the case. – Vladislavs Dovgalecs Nov 13 '15 at 06:47
-
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. – seanv507 Nov 13 '15 at 07:07
1 Answers
3
Tensors in the neural network community = vector (1D-tensor), matrix/array (2D-tensor), or multi-dimensional array (nD-tensor, with $n > 2$).
Examples:

Franck Dernoncourt
- 42,093
- 30
- 155
- 271