Output Layer
/ˈaʊtpʊt ˈleɪər/
The final layer of a neural network that produces predictions or outputs.
In italiano: Layer di OutputOutput layer size matches the number of target classes (classification) or output dimensions (regression). Uses appropriate activation: softmax for multi-class, sigmoid for binary, linear for regression.
Examples
- 10 neurons for digit classification
- 1 neuron for binary classification
- Multiple outputs for regression