Deep neural networks are the state-of-the-art for various applications. However,one of the biggest challenges facing them is the lack of labeled data to train these complex networks.

Nowadays integrated circuits (ICs) are underpinning all major information technology innovations including the current trends of artificial intelligence (AI).

Specifically, instead of directly measuring the divergence with paired images, we train a reward model with the dataset we construct, consisting of nearly 51,000 images annotated with human preferences.

Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated.

Simultaneously, convex formulations for training machine learning tasks have been replaced by nonconvex representations such as neural networks.