8.13 Getting started: Network anatomy

  • Training a neural network revolves around the following objects (see Figure 8.7, Chollet and Allaire (2018), Ch. 3)
    • Layers, which are combined into a network (or model)
    • The input data and corresponding targets
    • The loss function, which defines the feedback signal used for learning
    • The optimizer, which determines how learning proceeds.
A loss function measures the quality of the network’s output (Chollet & Allaire, 2018, Fig. 1.8)

Figure 8.7: A loss function measures the quality of the network’s output (Chollet & Allaire, 2018, Fig. 1.8)

References

Chollet, Francois, and J J Allaire. 2018. Deep Learning with R. 1st ed. Manning Publications.