by Michele Laurelli
The final layer of a neural network that produces predictions or outputs.
Output 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.
10 neurons for digit classification
1 neuron for binary classification
Multiple outputs for regression
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) that process information.
An activation function that converts a vector of values into a probability distribution summing to 1.
The output produced by a trained model when given new input data.