Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification

Saeid Asgari Taghanaki, Jeremy Kawahara, Brandon Miles, Ghassan Hamarneh

Abstract: Highlights•Traditionally, autoencoders are evaluated by their ability to reconstruct the input data.•We propose a new autoencoder optimization objective that also considers the classification performance of candidate encodings.•We optimize the multi-objective (reconstruction and classification errors) autoencoder using evolutionary computing (Non-dominated Sorting Genetic Algorithm-II).•We evaluate the performance of the proposed autoencoder using 949 mammograms and five different classifiers.•We demonstrate the proposed method achieves superior classification results compared to the traditional auto-encoders.