In Chapters 2, 3, 4 the network architecture, compilation and fitting steps are discussed. The first examples are of feedforward neural networks.
In the network architecture the layer_dense() and the activation function is used.
In the compilation steps the loss, the optimizer, and the metric is specified.
multidimensional arrays
In R columns are the primary way to look at arrays.
In Tensorflow rows are primary and the array_reshape() is used to prepare data for use with keras/tensorflow.
Be sure to read this section. The description of what neural networks try to do is very interesting.
See Figure 5.9
Derivatives in Calculus measure the rate of change of a function.
In multidimensional space derivatives are called gradients.
Gradients are used to minimize/maximize functions.
Four step process.
A neural network is composed of multiple tensor operations.
The backpropagation algorithm used the Chain Rule to implement the algorithm.
Try to get the examples from Chapter 4 to run.
Binary classification, movie reviews: The data preparation uses the Bag-of-Words model. All words in the reviews for the Dictionary or Bag-of-Words. Each word is given a number value.
Multi-class classification, newswires
Regression, predicting house prices.