Prof. Alfred Hero
University of Michigan，USA
Title: Immuno-mimetic Deep Neural Networks
Biomimetics has played a key role in the evolution of artificial neural networks. Thus far, in-silico metaphors have been dominated by concepts from neuroscience and cognitive psychology. In this talk we introduce a different type of biomimetic model, one that borrows concepts from the immune system, for designing robust deep neuralnetworks. This immuno-mimetic model leads to a new computational framework for robustification of deep neural networks against adversarial attacks. Within this Immuno-Net framework we define a robust adaptive immune-inspired learning system (RAILS) that emulates, in silico, the adaptive biological mechanisms of B-cells that are used to defend a mammalian host against pathogenic attacks.
Alfred O. Hero III is the John H. Holland Distinguished University Professor of Electrical Engineering and Computer Science and the R. Jamison and Betty Williams Professor of Engineering at the University of Michigan, Ann Arbor. His primary appointment is in the Department of Electrical Engineering and Computer Science and he also has appointments, by courtesy, in the Department of Biomedical Engineering and the Department of Statistics. He was founding Co-Director of the University’s Michigan Institute for Data Science (MIDAS) (2015-2018). He received the B.S. (summa cum laude) from Boston University (1980) and the Ph.D from Princeton University (1984), both in Electrical Engineering. He is a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) and the Society for Industrial and Applied Mathematics (SIAM). He is a Section Editor of the SIAM Journal on Mathematics of Data Science and a Senior Editor of the IEEE Journal on Selected Topics in Signal Processing . He is on the editorial board of the Harvard Data Science Review (HDSR) and is the moderator for the Electrical Engineering and Systems Science category of the arXiv . He has served as President of the IEEE Signal Processing Society and as a member of the IEEE Board of Directors. Alfred Hero has received numerous awards for his research and service to the profession including several best paper awards and the 2013 IEEE Signal Processing Society Technical Achievement Award, the 2015 Society Award from the IEEE Signal Processing Society and the 2020 Fourier Award from the IEEE. He received the 2017 Stephen S. Attwood Excellence in Engineering Award and the 2018 H. Scott Fogler Award for Professional Leadership and Service from the University of Michigan. Alfred Hero’s recent research interests are in high dimensional spatio-temporal data, multmodal data integration, statistical signal processing, and machine learning. Of particular interest are predictive mathematical models for the biological and physical sciences, social networks, network security and forensics, and personalized health and disease.
JD Explore Academy, China
Title: More Is Different: ViTAE elevates the art of computer vision
Big data contains a tremendous amount of dark knowledge. The community has realized that effectively exploring and using such knowledge is essential to achieving superior intelligence. How can we effectively distill the dark knowledge from ultra-large-scale data?
One possible answer is: "through Transformers". Transformers have proven their prowess at extracting and harnessing the dark knowledge from data. This is because more is truly different when it comes to Transformers. In this talk, I will showcase our recent work on transformers named ViTAE, on many dimensions of “more” including: model parameters, labeled and unlabeled data, prior knowledge, computing resource, tasks, and modalities.
Specifically, ViTAE has more model parameters and more input modality support; ViTAE can absorb and encode more data to extract more dark knowledge; ViTAE is able to adopt more prior knowledge in the form of biases and constraints; ViTAE can be easily adapted to larger-scale parallel computing resources to achieve faster training.
ViTAE has been applied to many computer vision tasks and has proven its promise, such as image recognition, object detection, semantic segmentation, image matting, pose estimation, scene text understanding, and remote sensing.
You can find the source code for this work at https://github.com/ViTAE-Transformer.
Dacheng Tao is the Inaugural Director of the JD Explore Academy and a Senior Vice President of JD.com. He is also an advisor and chief scientist of the digital science institute in the University of Sydney. He mainly applies statistics and mathematics to artificial intelligence and data science, and his research is detailed in one monograph and over 200 publications in prestigious journals and proceedings at leading conferences. He received the 2015 Australian Scopus-Eureka Prize, the 2018 IEEE ICDM Research Contributions Award, and the 2021 IEEE Computer Society McCluskey Technical Achievement Award. He is a fellow of the Australian Academy of Science, the World Academy of Sciences, the Royal Society of NSW, AAAS, ACM, IAPR and IEEE.
Prof. X. Sean Wang
Fudan University, China
Title: Democratizing the Full Data Analytics Software Stack
Data analysis and machine learning is a complex task, involving a full stack of hardware and software systems, from the usual compute systems, cloud computing and supercomputing systems, to data collection systems, data storage and database systems, data mining and machine learning systems, and data visualization and interaction systems. A realistic and highly efficient data analytics and AI application often requires a smooth collaboration among the different systems, which becomes a big technical hurdle, especially to the non-computing professionals. The history of computing may be viewed as a technical democratizing processing, which in turn brings huge benefit to the society and its economy. The democratizing process for data analysis and machine learning has started to appear in various aspects, but it still needs research and development in multiple directions, including human-machine natural interaction, automated system selection and deployment, and automated workflow execution and optimization. It can be expected that this democratizing process will continue, and the research and development efforts by the computer scientists are much needed.
X. Sean Wang is Professor at the School of Compute Science, Fudan University, a CAAI and CCF Fellow, ACM Member, and IEEE Senior Member. His research interests include data analytics and data security. He received his PhD degree in Computer Science from the University of Southern California, USA. Before joining Fudan University in 2011 to be the dean of its School of Computer Science and the Software School, he served as the Dorothean Chair Professor in Computer Science at the University of Vermont, USA, and as a Program Director at the National Science Foundation, USA. He has published widely in the general area of databases and information security, and was a recipient of the US National Science Foundation CAREER award. He’s a former chief editor of the Springer Journal of Data Science and Engineering. He’s currently on the steering committees of the IEEE ICDE and IEEE BigComp conference series, and past Chair of WAIM Steering Committee.
Prof. Xin Yao
Research Institute of Trustworthy Autonomous Systems (RITAS)
Southern University of Science and Technology (SUSTech), Shenzhen, China
School of Computer Science, University of Birmingham, UK
Title: Multi-objective Learning and Its Applications
Most, if not all, machine learning problems are defined by a single loss function. Yet the vast majority of these loss functions have two or more terms summed together through hyper-parameters. A closer examination of these loss functions should reveal that there are in essence two or more conflicting objectives that a loss function tries to minimise, e.g., accuracy and regularisation. This talk treats a multi-objective problem as a multi-objective problem, rather than trying to combined them into a single loss function through a weighted sum. While the weighted sum approach might appear simpler, it does require additional time and effort to tune hyper-parameters, which could be seen as the coefficients to balace different objectives. The talk describes how existing multi-objective evolutionary algorithms could be used as multi-objective learning algorithms, the natural link between multi-objective learning and ensemble learning, and selected examples of multi-objective learning in different domains. It is argued that multi-objective learning can be an effective approach towards achieving different trade-off in various practical learning scenarios.
Xin Yao is a Chair Professor of Computer Science at the Southern University of Science and Technology, Shenzhen, China, and a part-time Professor of Computer Science at the University of Birmingham, UK. His major research interests include evolutionary computation, ensemble learning and search-based software engineering. More recently, he has been working on AI ethics, especially fairness. He is an IEEE fellow, a former (2014-15) president of IEEE Computational Intelligence Society (CIS) and a former (20003-08) Editor-in-Chief of IEEE Transactions on Evolutionary Computation. His research work won the 2001 IEEE Donald G. Fink Prize Paper Award, 2010, 2016 and 2017 IEEE Transactions on Evolutionary Computation Outstanding Paper Awards, 2010 BT Gordon Radley Award for Best Author of Innovation (Finalist), 2011 IEEE Transactions on Neural Networks Outstanding Paper Award, and many other best paper awards. He received a Royal Society Wolfson Research Merit Award in 2012, the IEEE CIS Evolutionary Computation Pioneer Award in 2013, and the 2020 IEEE Frank Rosenblatt Award.