The design of suitable network architectures is a challenging and time-consuming task. Therefore, automatic discoveryand optimization of neural networks is considered important for continuing the trend of moving classification tasksfrom cloud to edge computing.In this project an evolutionary method to optimize a convolutional neural network (CNN) architecture for classificationtasks has been developed. The method runs efficiently on a single GPUworkstation and provides simple means todirect the tradeoffbetween complexity and accuracy of the evolved network. Using this method, we achieved a 11xreduction in the number of multiply-accumulate (MAC) operations of the winning network for the German Traffic SignRecognition Benchmark (GTSRB) without accuracy reduction. An ensemble of four of our evolved networks competesthe winning ensemble with a 0.1% lower accuracy but 70x reduction in MACs and 14x reduction in parameters. In asecond stage of this project, the method has been extended to perform hardware-aware CNN architecture search foran inference accelerator method based on binary approximation of CNN weights.