Hands-On ROS for Robotics Programming

The hidden layer(s)

For understanding how this layer works, let's go back to the regression algorithm we explain earlier. There, we expressed the predicted variable as a linear combination of features—area, number of rooms, and distance to the center multiplied by weights, respectively, W1, W2, and W3. Establishing the analogy with our neural network, the features would apply to the neurons and the weights to the edges that connect each pair of neurons:

Source: https://commons.wikimedia.org/wiki/File:Artificial_neural_network_pso.png, Cyberbotics Ltd. CC BY-SA 3.0 https://creativecommons.org/licenses/by-sa/3.0

The value of each feature would ...