Found this excellent video on YouTube by Prof. Daniel Fleisch that explains tensors in a very simple and engaging way - https://youtu.be/f5liqUk0ZTw
Tensors are are generalizations of vectors & matrices to N-dimensional space.
- A scalar is a 0 dimensional tensor
- A vector is a 1 dimensional tensor
- A matrix is a 2 dimensional tensor
- A nd-array is an N dimensional tensor
The inputs, outputs, and transformations within neural networks are all represented using tensors. A tensor can be visualized as a container which can house data in N dimensions.
No comments:
Post a Comment