A linear perceptron has been trained with a set of n points (∈ ℝ²) and their corresponding labels (∈ {-1, 1}). The order of the samples is unknown. However, for each point the number mistakes made by the algorithm until the convergence has been reached are provided.
Assuming weight and bias initialized with zeros, how to calculate the weight and bias values after training convergence? Is it possible to derive the exact order of the samples?
