526互联

SciTech-BigDataAIML-Tensorflow-Introduction to Gradients and Automatic Differentiation

发布时间 2024-01-02 16:02:14作者: abaelhe

In this guide, you will explore ways to compute gradients with TensorFlow, especially in eager execution.

Automatic Differentiation and Gradients
Automatic differentiation is useful for implementing machine learning algorithms such as backpropagation for training neural networks.

Computing gradients
To differentiate automatically, TensorFlow needs to:

  • remember what operations happen in what order during the forward pass.
  • Then, during the backward pass, TensorFlow traverses this list of operations in reverse order to compute gradients.