MathematicsLesson 50Free preview

Tensors

This lesson is part of A.I. · All levels

Summary

Tensor is the generalization of scalars, vectors, and matrices to a larger number of dimensions. Scalars are 0, vectors are 1, matrix is 2, and so on. Deep learning works fully on tensors, so libraries like TensorFlow are named after these data structures.

Key points

Scalar is 0-dimensional tensor, vector is 1-dimensional, matrix is 2-dimensional.
The three-dimensional tensor can be used for layered data like RGB images.
The shape property shows the size of each tensor dimension.
The sum of the tensor elements is the multiplication of the whole number on its shape.
The weight of each layer of the neural network is stored as a tensor.

Full lesson

Code examples and quizzes

Full lessons, code examples, and quizzes are available to subscribers. 5 questions.