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?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.