Wang, HongmingJaume, SylvainDarnowsky, Philip2022-02-0820222022-02-072022Darnowsky, Philip. 2022. Image Classification with Evolved Convolutional Neural Networks. Master's thesis, Harvard University Division of Continuing Education.28966797https://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37370755Convolutional neural networks (CNNs) are a well-established technique for image classification problems. While the topology of a CNN strongly affects the performance of that CNN, designing a CNN’s topology remains a difficult task, often with nothing better than some empirical rules-of-thumb for guidance. Evolutionary algorithms are a family of metaheuristics that can be applied to optimization problems where good solutions are hard to create from first principles, but the quality of a given solution is easy to measure. In this research, we develop and evaluate several variations on an algorithm, SDAG, which applies evolutionary methods to finding performant topologies for CNN-based image classifiers.application/pdfenComputer visionConvolutional neural networks (CNNs)Evolutionary algorithmsImage classificationMachine learningNeural network topologyComputer scienceArtificial intelligenceApplied mathematicsThesis or Dissertation2022-02-08