tf.keras and TensorFlow: Batch Normalization to train deep neural networks faster | by Chris Rawles | Towards Data Science
![Creating Custom Estimators in TensorFlow — Google for Developers Blog - News about Web, Mobile, AI and Cloud Creating Custom Estimators in TensorFlow — Google for Developers Blog - News about Web, Mobile, AI and Cloud](https://1.bp.blogspot.com/-6AyXU0jwiHc/WjmL2DHU6MI/AAAAAAAAEXo/mitX7ph45t0CcHEDw5p3J8BgmUVh2K12wCLcBGAs/s1600/full_network.png)
Creating Custom Estimators in TensorFlow — Google for Developers Blog - News about Web, Mobile, AI and Cloud
![machine learning - What is the point of having a dense layer in a neural network with no activation function? - Cross Validated machine learning - What is the point of having a dense layer in a neural network with no activation function? - Cross Validated](https://i.stack.imgur.com/R3hsF.png)
machine learning - What is the point of having a dense layer in a neural network with no activation function? - Cross Validated
What is the difference b.t. tf.layers.dense and tf.layers.Dense · Issue #22020 · tensorflow/tensorflow · GitHub
![tensorflow - Custom loss function in Keras that penalizes output from intermediate layer - Stack Overflow tensorflow - Custom loss function in Keras that penalizes output from intermediate layer - Stack Overflow](https://i.stack.imgur.com/r0SWl.png)