Deep neural network architecture search using network morphism


The paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification problem. We compared the parameters and performance of the automatically generated neural structure with the architectures selected manually, reported by the authors in previous papers. The obtained structure achieved comparable results to hand-designed networks, but with much fewer parameters then manually crafted architectures.

In 24th International Conference on Methods and Models in Automation and Robotics (MMAR)