Hidden Layer

The hidden layer is a layer that processes and transforms data received from the input layer.

It plays a crucial role in the transformation of simple data into complex patterns within neural networks.

In a hidden layer, weights and activation functions are used to adjust input data.

For example, when processing 5×5 sized data from the input layer, the hidden layer applies specific operations to transform these values before passing them to the next layer.

Below is an example illustrating how pixel values from the input layer are transformed in the hidden layer.

Copy
[
  [0.1, 0.3, 0.9, 0.3, 0.1],
  [0.3, 0.7, 0.2, 0.7, 0.3],
  [0.9, 0.2, 0.1, 0.2, 0.9],
  [0.3, 0.7, 0.2, 0.7, 0.3],
  [0.1, 0.3, 0.9, 0.3, 0.1]
]

Here, the values changed to between 0-1 due to the activation function.

Also, the numbers have altered because the weights adjusted the inputs as the neural network learned the data.

This transformed data helps in learning higher-level features and is ultimately used in the output layer to derive the desired result.