• Hefei Qiu: It’s an analogy that goes back to the dawn of the computer era: ever since we discovered that machines could solve problems by manipulating symbols, we’ve wondered if the brain might work in a similar fashion.
• Yong Zhuang: In particular, the gradient does not provide information useful in distinguishing between local errors without future consequences and cascading errors which are more serious.
• Wei Ding: AI is the universal connector that interweaves all of our Big Ideas; data science is changing the very nature of scientific inquiry, and AI’s use of data has the potential to revolutionize everything we do in science.
• Chengjie Zheng: Linear evaluation of models with varied depth and width. Models in blue dots are ours trained for 100 epochs, models in red stars are ours trained for 1000 epochs, and models in green crosses are supervised ResNets trained for 90 epochs.
• Zihan Li: This is primarily because of the black-box nature of conventional deep learning frameworks, that are learned solely from data and are agnostic to the underlying scientific principles driving real-world phenomena.