Series Seminar of SAI in 2020(I) -- Academic Lecture by Amy from Singapore Management University

Title: One-Class Order Embedding Learning for Dependency Relation PredictionTime: 10: 00am, Friday, January 3, 2020Venue: Administration Building, Room 601Abstract:Most of current representation learning techniques aim to learn entity representations that are semantics-preserving, i.e., semantically similar entities are mapped into a nearby area in the semantic embedding space. In this study, w...

Series Seminar of SAI in 2020(IV) -- Academic Lecture by Postdoc Sudao Bilige from The University of Sydney

​Title: Application of Artificial Intelligence and Robotics in Precision AgricultureTime: 10: 00am, Thursday, January 9, 2020Venue: Administration Building, Room 601Organizer: School of Artificial Intelligence Abstract: Agricultural Automation, Robotization and Artificial Intelligence will greatly reduce labor costs, increase the utilization of fertilizers and other pesticides, reduce environm...

Series Seminar of SAI in 2020(III) -- Academic Lecture by Professor Jian Yu from Beijing Jiaotong University

Title: Cognition-based Machine Learning AxiomatizationTime: 10: 00am, Friday, January 10, 2020Venue: Administration Building, Room 601Organizer: School of Artificial IntelligenceAbstract: In the era of big data, a large number of new machine learning methods, driven by application requirements, are constantly generated. These new algorithms have different theoretical basis, and the relationship...

Series Seminar of SAI in 2020 (II) -- Academic Report of Dr. Ming Liu from Monash University

​Title: Learning Deep Neural Networks for Hard Natural Language ProblemsAbstract: Deep learning has revolutionized the way that many tasks are tackled in Natural Language Processing (NLP). This talk will cover some recent advances in deep learning for NLP, including embeddings, encoder-decoder architecture, attentions, and language modeling. Then, I will introduce some of the research work in ...

Academic Report of Dr. Shixia Liu from Tsinghua University

Title: Interpretable Machine Learning Based on Visual AnalysisAbstract: Interpretable machine learning aims to make the decision-making process of machine learning models more transparent to researchers and practitioners, so as to achieve effective communication and collaboration between human and machine. This report will introduce our visual analysis framework for machine learning models. Thi...

Academic Report of Dr. Jielong Yang from Nanyang Technological University

Title: On Truth Finding in Multi-agent NetworksAbstract: A problem named “truth-finding” will be discussed in this talk. In this problem, an event is a phenomenon of interest and our goal is to infer the states of events (e.g., articles, movies, and signals) through biased observations of multiple agents (e.g., sensors and individuals) in a network. The local bias of each agent is unknown and...

Academic Report of Assistant Lecturer Xingjun Ma from University of Melbourne

Title: Adversarial Machine Learning: an introduction and tutorialAbstract: Deep learning has become increasingly popular in the past few years. This is largely attributed to a family of powerful models called deep neural networks (DNNs). With many stacked layers, and millions of neurons, DNNs are capable of learning complex non-linear mappings, and have demonstrated near or even surpassing huma...

Academic Report of Prof. Zhaojian Li from Michigan State University

Talk I:Future Mobility: Integrating Data-Driven and Control Methods into Automotive Decision-Making SystemsTime:Monday, 16 December 2019 9:00 a.m. to 11:00 a.m.Venue: Lecture Hall, 2nd Floor, Zoon A, Advanced Control Base, Nanling CampusAbstract: Data is everywhere. Modern vehicles are equipped with hundreds of sophisticated sensors that offer necessary information for various functionalities. ...

Academic Report of Dr. Boyuan Chen from Columbia University, USA

Title: Machine Theory of Behavior and MindAbstract: We have seen impressive results from machine learning that enable machines to recognize objects very accurately, translate between multiple languages, and manipulate various objects with a high success rate. However, there is still a gap to build machines that can operate in an unconstrained environment. Humans can understand the goal, intenti...

Academic Report of Dr. Euijin Alley Choo from Qatar Computing Research Institute

Title: Data-driven Cyber Security IntelligenceSpeaker: Euijin Alley ChooTime: 10:00, Monday, August 26, 2019Venue: Conference Room 601, Administration BuildingBiography:       Dr. Euijin Alley Choo is a postdoctoral researcher at Qatar Computing Research Institute (QCRI). Before joining QCRI, she worked as a research professor at Korea University and a visiting assistant professor at the Univer...