Approximate computing for resource efficient on-device neural network trainingCiglarič, Timotej (Avtor) Pejović, Veljko (Mentor) Machidon, Octavian Mihai (Komentor) convolutional neural networksperforated convolutionapproximated trainingsustainable computingAI on the edgeSince most neural network approximation techniques are limited to inference, we work to adapt it for practical usage during training, establishing options for training on weaker edge devices. We build on previous work to expand upon perforated convolution as a neural network approximation technique as well as adapt it for use during training. We speed up convolutional layers by skipping their evaluation and gradient calculation in some spatial positions, then interpolating the missing values. We analyze the effect of using perforated convolution during training. We show that on weak edge devices, using perforated convolution training with segmentation networks such as AgriAdapt U-Net reduces memory usage by up to 30% with up to 5x speedup, with a significant reduction in training energy usage.20262026-02-02 13:20:02Magistrsko delo/naloga178939VisID: 37924COBISS_ID: 283318531sl