Memetic evolution of deep neural networks

Deep neural networks (DNNs) have proven to be effective at solving challenging problems, but their success relies on finding a good architecture to fit the task. Designing a DNN requires expert knowledge and a lot of trialand error, especially as the difficulty of the problem grows. This paper proposes a fully automatic method with the goal of optimizing DNN topologies through memeticevolution. By recasting the mutation step as a series of progressively refinededucated local-search moves, this method achieves results comparable to best human designs. Our extensive experimental study showed that the proposed memetic algorithmsupports building a real-world solution for segmenting medical images, it exhibits very promising results over a challenging CIFAR-10 benchmark, and works very fast. Given the ever growing availability of data, our memetic algorithmis a very promising avenue for hands-free DNN architecture design to tackle emerging classification tasks.