特邀报告

Professor Jixin Ma

School of Computing and Mathematical Sciences, the University of Greenwich
Speech Title: Temporal Issues in Information Processing
Abstract:
The notion of time plays an important role in modelling natural phenomena and human activities concerning the dynamic aspect of the real world. Virtually most information in the universe of discourse is time-dependent and suitable methodologies are needed to deal with the rich temporal issues in information processing. In particular, many information systems need to deal with the temporal dimension of information, the change of information over time and the knowledge about how it changes. The purpose of this talk is to: (a) motivate and explain a topic of emerging importance in information processing; (b) provide an overview on some fundamental issues with respects to temporal ontology; (c) present a brief introduction to temporal representation and reasoning in information processing in terms of some illustrating examples. It is hoped that this speech will raise some special interests in representing and reasoning about the temporal issues in information processing. ...View More

Assistant Professor Jun Zhao

School of Computer Science and Engineering (SCSE), Nanyang Technological University (NTU)
Speech Title: The New Dawn of AI: Federated Learning
Abstract: Federated learning was proposed by Google in 2017. The idea is that different parties (e.g., different organisations, or different mobile devices) can collaboratively train a machine learning model without sharing the raw data. Compared with the case where the parties share the raw data directly, federated learning provides a certain level of privacy protection, as each party’s raw data is not sent out and is used for local training. The iterative training process of federated learning works as follows. In each iteration, each one from a set of parties conducts local training, and then the local updates of the parties are aggregated to update the global model. Since its proposal, federated learning has been a booming field for research and development. In about 3 years, there have been over 1000 papers related to federated learning. Also, tech giants are building various federated learning software: TensorFlow Federated by Google, FATE (Federated AI Technology Enabler) by Webank, Clara Training by NVIDIA, and PaddleFL by Baidu. In this talk, I will give an introduction of federated learning. ...View More

Software engineer Tao Lin

Amazon, Seattle
Speech Title: Deep Learning in Security
Abstract: Deep learning and other machine learning approaches are deployed to many systems related to Internet of Things or IoT. However, it faces challenges that adversaries can take loopholes to hack these systems through tampering history data. This talk first presents overall points of adversarial machine learning. Then, we illustrate traditional methods, such as Petri Net cannot solve this new question efficiently. After that, this talk uses the example from triage(filter) analysis from IoT cyber security operations center. Filter analysis plays a significant role in IoT cyber operations. The overwhelming data flood is obviously above the cyber analyst’s analytical reasoning. To help IoT data analysis more efficient, we propose a retrieval method based on deep learning (recurrent neural network). Besides, this talk presents a research on data retrieval solution to avoid hacking by adversaries in the fields of adversary machine leaning. It further directs the new approaches in terms of how to implementing this framework in IoT settings based on adversarial deep learning. ...View More

Professor Vijayakumar Varadarajan

University of New South Wales
Speech Title: coming soon
Abstract:coming soon