2022 International conference on Cloud Computing, Performance Computing and Deep Learning (CCPCDL 2022) has been successfully held on March 11, 2022, , which is a virtual conference.
There were about 100 delegates attended the online conference, several experts in related fields were invited to give keynote speeches. The in-depth discussions among the attendees effectively advanced the academic exchange.
Group Photo |
At the same time, We have invited 4 respectable professors to deliver an unusual keynote addresses at the plenary meeting, consisting of Prof. Daowen Qiu (Sun Yat-sen University, China), Prof. Yuanzhu Chen, (School of Computing, Queen's University, Canada), Prof. Sandeep Saxena(Department of Information Technology, Galgotias College of Engineering and Technology, Greater Noida, Inda.), Prof. Xiaofeng Ding(Huazhong University of Science and Technology, China ).
Keynote Speakers | |
1. Prof. Yuanzhu Chen | Title: Fading Networks Abstract: The universal presence of networks makes them an important conduit to study interactions in complex natural and artificial systems. While maintaining their integrity is crucial, in many cases, we are also interested in disconnecting them for disease prevention control, failure containment, crime disruption, etc. With an array of methods exploring node importance, localized execution, measurement of fragmentation, the choices we have can be disorienting. In this talk, I will discuss a general framework proposed to investigate strategic choices of nodes to remove from the network, and how distributed information gathering and decision making can help us achieve the balance between efficacy and cost of doing so. The framework was evaluated using computer simulation of network dissolution for the full process of weakening, breaking, and shattering. Measurements of focus include the structural losses such as increased effective diameter, homogenization of node degrees, and Shannon diversity of resultant network fragments. I will also review a few other projects of mine related to computer networking and complex networks. |
2. Prof. Daowen Qiu | Title: Quantum Model Learning Abstract: Learning finite automata (termed as model learning) has become an important field in machine learning and has been useful realistic applications. Quantum finite automata (QFA) are simple models of quantum computers with finite memory. Due to their simplicity, QFA have well physical realizability, but one-way QFA still have essential advantages over classical finite automata with regard to state complexity. As a different problem in quantum learning theory and quantum machine learning, in this talk, we introduce learning QFA (both MO-1QFA and MM-1QFA are simple but important QFA) with queries (naturally it is termed as quantum model learning), including: (1) A learning algorithm for measure-once one-way QFA (MO-1QFA) with query complexity of polynomial time; (2) A learning algorithm for measure-many one-way QFA (MM-1QFA) with query complexity of polynomial-time, as well. |
3. Prof. Sandeep Saxena | Title: Permissioned Blockchain Abstract: A blockchain is an immutable transaction ledger, maintained within a distributed network of peer nodes. These nodes each maintain a copy of the ledger by applying transactions that have been validated by a consensus protocol, grouped into blocks that include a hash that bind each block to the preceding block. A permissioned blockchain is a distributed ledger that is not publicly accessible. It can only be accessed by users with permissions. The users can only perform specific actions granted to them by the ledger administrators and are required to identify themselves through certificates or other digital means. |
4. Prof. Xiaofeng Ding | Title: Privacy Preserving Problems in Deep Learning Abstract: Deep learning is increasingly popular, partly due to its widespread application potential, such as in civilian, government and military domains. Given the exacting computational requirements, cloud computing has been utilized to host user data and model. However, such an approach has potential privacy implications. Therefore, we introduce a method to protect user’s privacy in the inference phase of deep learning workflow. Specifically, we use an intermediate layer to separate the entire neural network into two parts, which are respectively deployed on the user device and the cloud server. |
Oral Speakers | |
1. Yuting Wu | 2. Chenchen Ao |
3. Sheng Jia | 4. Xiaoyang Liu |
5. Huishuang Xing | 6. Shilin Li |
7. Huishuang Xing | 8. Huishuang Xing |
9. Huishuang Xing | 10. Lutong Dong |
Previous Publication