TensorFlow

TensorFlow is an example of deep learning, a neural network that has many layers. It is a software library developed by the Google Brain Team.

Deep Learning Neural Network

Image borrowed from: http://www.kdnuggets.com/2017/05/deep-learning-big-deal.html

Terminology: Tensors

A Tensor is a multi-dimensional array.

Example: A sequence of images can be represented as a 4-D array: [image_num, row, col, color_channel]

Terminology: Computational Graphs

Computational graphs help to break down computations.
- For example, the graph for $y=(x1+x2)*(x2 - 5)$:

The beauty of computational graphs is that they show where computations can be done in parallel.

The Need for GPUs

With deep learning models, you can have hundreds of thousands of computational graphs. A GPU has the ability to perform a thousand or more of the computational graphs simultaneously. This will speed up your program significantly.

Note: Most algorithms can run without GPUs, but they will be slower.

Last updated on Jun 9, 2022