A Melting Pot of Evolution and Learning
This work addresses the integration of evolutionary methods with machine learning for researchers and practitioners, but it is incremental as it surveys existing contributions rather than presenting new findings.
This paper surveys eight recent works that blend evolutionary algorithms with machine learning and deep learning, tackling problems like classification, adversarial attacks, and tool development, with results including novel algorithms and successful applications in image classification and object detection.
We survey eight recent works by our group, involving the successful blending of evolutionary algorithms with machine learning and deep learning: 1. Binary and Multinomial Classification through Evolutionary Symbolic Regression, 2. Classy Ensemble: A Novel Ensemble Algorithm for Classification, 3. EC-KitY: Evolutionary Computation Tool Kit in Python, 4. Evolution of Activation Functions for Deep Learning-Based Image Classification, 5. Adaptive Combination of a Genetic Algorithm and Novelty Search for Deep Neuroevolution, 6. An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks, 7. Foiling Explanations in Deep Neural Networks, 8. Patch of Invisibility: Naturalistic Black-Box Adversarial Attacks on Object Detectors.