No.	Date	Contents	Reference	Video
1	2022/03/16	AI Seminar: Physics-Informed Machine Learning​	Stoudenmire, E. & Schwab, D. J. Supervised learning with tensor networks. Adv. Neural Inf. Process. Syst. 29, 4799–4807 (2016). Mathews, A., Francisquez, M., Hughes, J. & Hatch, D. Uncovering edge plasma dynamics via deep learning from partial observations. Preprint at arXiv https://arxiv.org/abs/2009.05005 (2020). Shukla, K., Di Leoni, P. C., Blackshire, J., Sparkman, D. & Karniadakis, G. E. Physics-informed neural network for ultrasound nondestructive quantification of surface breaking cracks. J. Nondestruct. Eval. 39, 1–20 (2020). Lu, L. et al. Extraction of mechanical properties of materials through deep learning from instrumented indentation. Proc. Natl Acad. Sci. USA 117, 7052–7062 (2020). Xu, Z.-Q. J., Zhang, Y., Luo, T., Xiao, Y. & Ma, Z. Frequency principle: Fourier analysis sheds light on deep neural networks. Commun. Comput. Phys. 28, 1746–1767 (2020). Rahaman, N. et al. On the spectral bias of neural networks. Proc. Int. Conf. Mach. Learn. 97, 5301–5310 (2019). Wang, S., Yu, X. & Perdikaris, P. When and why PINNs fail to train: a neural tangent kernel perspective. Preprint at arXiv https://arxiv.org/abs/2007.14527 (2020). Wang, S., Wang, H. & Perdikaris, P. On the eigenvector bias of Fourier feature networks: from regression to solving multi- scale PDEs with physics- informed neural networks. Preprint at arXiv https://arxiv.org/abs/2012.10047 (2020). Wang, S., Teng, Y. & Perdikaris, P. Understanding and mitigating gradient pathologies in physics-informed neural networks. Preprint at arXiv https://arxiv.org/abs/2001.04536 (2020). Link ​ppt	Link
2	2022/04/06	AI Seminar--An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2021). Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377. Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., & Houlsby, N. (2020). Big transfer (bit): General visual representation learning. arXiv preprint arXiv:1912.11370 Yannic Kilcher (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained). Retrieved from https://youtu.be/TrdevFK_am4 科技猛兽 (2021). Vision Transformer 超详细解读 (原理分析+代码解读) (二) Retrieved from https://zhuanlan.zhihu.com/p/342261872 AppleHank (2020). ViT — Vision Transformer : Convolution is dead, long live Transformers! Retrieved from https://applehank.medium.com/vit-vision-transformer-convolution-is-dead-long-live-the-self-attention-bbced72a8487 https://github.com/google-research/vision_transformer/ https://github.com/lucidrains/vit-pytorch ppt	Link
3	2022/06/01	Seminar on Artificial Intelligence for Engineering Applications – Capsule Networks	Sabour, S., Frosst, N., & Hinton, G. E. (2017). Dynamic routing between capsules. Advances in neural information processing systems, 30. Pechyonkin, M. (2017) Understanding Hinton’s Capsule Networks, retrieved May 19, 2022, from: https://medium.com/ai%C2%B3-theory-practicebusiness/understanding-hintons-capsule-networks-part-iii-dynamic-routingbetween-capsules-349f6d30418 Lee, H. Y. (2017). Capsule, Deep Learning Online Course, retrieved May 19, 2022, from: https://www.bilibili.com/video/BV1Qx411V75M/ Géron, A. (2017). Capsule Networks (CapsNets) – Tutorial, retrieved May 19, 2022, from: https://www.youtube.com/watch?v=pPN8d0E3900 Bielski, A. (2019). Dynamic Routing Between Capsules - PyTorch implementation, retrieved May 19, 2022, from: https://github.com/adambielski/CapsNet-pytorch Xinyi, Z., & Chen, L. (2018). Capsule graph neural network. International conference on learning representations, Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. ppt	Link