The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution. By extending existing neuroevolution methods to topology, components, and hyperparameters, this method achieves results comparable to the best human designs in standard benchmarks in object recognition and language modeling. It also supports building a real-world application of automated image captioning on a magazine website. Given the anticipated increases in available computing power, evolution of deep networks is a promising approach to constructing deep learning applications in the future.

PDF

To Appear In R. Kozma, C. Alippi, Y. Choe, and F. Morabito, editors, Artificial Intelligence in the Age of Neural Networks and Brain Computing (second edition), New York, 2023. Elsevier.

@incollection{miikkulainen:chapter23, title={Evolving Deep Neural Networks}, author={Risto Miikkulainen and Jason Liang and Elliot Meyerson and Aditya Rawal and Dan Fink and Olivier Francon and Bala Raju and Hormoz Shahrzad and Arshak Navruzyan and Nigel Duffy and Babak Hodjat}, booktitle={Artificial Intelligence in the Age of Neural Networks and Brain Computing (second edition)}, month={ }, editor={R. Kozma and C. Alippi and Y. Choe and F. Morabito}, address={New York}, publisher={Elsevier}, url="http://nn.cs.utexas.edu/?miikkulainen:chapter23", year={2023} }