Abstract: A transmission line can include a first conductive line, a second conductive line, a signal line disposed between the first conductive line and the second conductive line, with a first gap between the signal line and the first conductive line, and a second gap between the signal line and the second conductive line. A first shield can be disposed directly over a portion of the first gap, and a second shield can be disposed directly over a portion of the second gap. A slot can separate the first shield from the second shield. The transmission line can be a coplanar waveguide.

Abstract: A transmission line can include a first conductive line, a second conductive line, a signal line disposed between the first conductive line and the second conductive line, with a first gap between the signal line and the first conductive line, and a second gap between the signal line and the second conductive line. A first shield can be disposed directly over a portion of the first gap, and a second shield can be disposed directly over a portion of the second gap. A slot can separate the first shield from the second shield. The transmission line can be a coplanar waveguide.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for jointly determining neural network architectures and hardware accelerator architectures.

Abstract: The present disclosure provides a differentiable joint hyper-parameter and architecture search approach, with some implementations including the idea of discretizing the continuous space into a linear combination of multiple categorical basis. One example element of the proposed approach is the use of weight sharing across all architecture- and hyper-parameters which enables it to search efficiently over the large joint search space. Experimental results on MobileNet/ResNet/EfficientNet/BERT show that the proposed systems significantly improve the accuracy by up to 2% on ImageNet and the F1 by up to 0.4 on SQuAD, with search cost comparable to training a single model. Compared to other AutoML methods, such as random search or Bayesian method, the proposed techniques can achieve better accuracy with 10× less compute cost.