Lecture
This lecture presents U-Boost NAS, a method that boosts resource utilization in neural architecture search by modeling resource utilization in inference platforms, proposing a smooth approximation of the ceiling function, and introducing a multi-objective loss function. The lecture also covers hierarchical three-stage NAS, CIFAR10 and ImageNet 100 experiments, and a comparison of U-Boost with baselines in cell microarchitecture and channel dimensions.