Abstract: Gallium nitride (GaN) transistors enable efficient and compact high-voltage power converters. In the state-of-the-art enhancement mode GaN-on-Si technology, a 650-V power transistor is ...
Abstract: Gallium nitride (GaN) devices are revolutionarily advancing the efficiency, frequency, and form factor of power electronics. However, the material composition, architecture, and physics of ...
Abstract: There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks. We provide evidence against this claim and build ...
Abstract: Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator ...