Title: Quantum Knowledge Representation Quantum encryption is known to be very secure, since if it is interfered by the third party the original information cannot be restored. In this lecture, I begin from the fundamentals of quantum mechanics, and then expound quantum computation, including quantum logic. The quantum computation lies in several mysterious notions such as qubit, superposition, entanglement, and so on. Among which, I especially consider the superposition and discuss how it can be applied to knowledge representation in AI. I refer to an example of a detective story, and show that knowledge can only be retrieved in the probabilistic manner in agent communication.

Title: Beyond Performance Benchmarking: Towards Explainable and Rationalized NLP Systems Recently, large pretrained language models have brought revolutionary performance improvements in a wide range of NLP tasks. However, two important, long-standing issues have not been fully solved yet: (i) Explainability: NLP systems cannot explain their own reasoning. (ii) Rationality: part of the performance improvement is attributed to spurious cues in the training dataset. In this talk, l will give a broad overview of these research areas, including a basic discussion of explainability and rationality, and previous efforts for addressing these two issues. I then discuss possible future directions towards explainable and rationalized NLP systems.

Title: Explanation in AI (not only ML): From ML to KRR and Beyond Explainable AI is not a new topic. The earliest work on Explainable AI could be found in the literature published 40 years ago, where expert systems explained their results via the applied rules or by backtracking the reasoning. Since AI research began, scientists have argued that intelligent systems should explain the AI results, mostly when it comes to decisions.
In this lecture, I begin from knowledge representation formalisms in AI, and traditional machine learning approaches to the latest progress in the context of modern deep learning, and then describes the major research areas and the state-of-the-art approaches in recent years.
Three main topics will be covered in this lecture:
(1) interpretability and explainablity in logic-based AI,
(2)interpretability and explainbility in machine learning, and
(3) interpretability and explainability in hybrid AI that synergises logic with machine learning. The lecture ends with a discussion on challenges and future directions.

Title: Deep learning for NLP and its application In this tutorial, we aim to present our survey on deep learning for NLP.
We will discuss the fundamental knowledge of deep learning and its application for NLP.
We then show how deep learning techniques can be applied for various important applications in NLP, such as question and answering and machine translation.
The lecture consists of the following parts.
1. Introduction to Deep Learning
2. Introduction to Natural language processing
3. Deep learning for NLP
4. NLP applications with Deep Learning techniques

Title: Malware Analysis For developing binary code tools, understanding the formal semantics of instruction sets is needed. There are various instruction sets, especially for IoT devices.
In this presentation, we will briefly introduce our recent trial of automatic formal semantics extraction by NLP on manuals, which comes during the development of symbolic execution tools for analyzing malware, e.g., BE-PUM for x86, SyMIPS for MIPS, and CORANA for ARM.

Title: Prescriptive Analytics - From Conventional Methods to AI-assisted Problem Solving This lecture will provide an overview of prescriptive analytics and data-driven optimisation.
Key elements of optimisation problems will be discussed and the challenges of solving real-world optimisation problems will be highlighted.
Most popular solutions approaches tor optimisation such as mathematical optimisation, heuristics, meta-heuristics, and hyper-heuristics are reviewed and their connections will be discussed.
Then, we will look at optimisation problems from the lens of modern AI algorithms and technologies and discuss recent research attempting to develop novel ways to solve large-scale, dynamic, stochastic, and complex optimisation problems. Some case studies will be presented in this lecture.