Teaching

Course Description

1. I239E Machine Learning, School of Information Science, JAIST

First, we give a fundamental of machine learning, and mathematical fundamentals used in machine learning. Next, we teach algorithms of supervised learning and unsupervised learning as a standard methodology of machine learning. Understanding these algorithms make the students acquire a fundamental skill to use machine learning technique. Thereafter, we give fundamentals and application of deep learning as a modern machine learning method. Then, the students would be able to understand how does machine learning work, and how does machine learning apply on practical problem setting.

2. I628E Information Processing Theory, School of Information Science, JAIST

We introduce advanced research topics in some different disciplines of Information Science, which include Technology behind synthetic singers (Akagi), Attention system and auditory system (Kidani), Interpretability and explainability in AI (Racharak), Graph theoretic circuit theory (Kaneko), Internet of energy and power flow management (Javaid), and New technologies on internet construction (Uda).

Teaching in FY 2023

1. I239E Machine Learning, School of Information Science, JAIST

2. Basic description logics, ReaLearn (Trustworthy Lab), JAIST

3. Basic argumentation, ReaLearn (Trustworthy Lab), JAIST

Teaching in FY 2022

1. I239E Machine Learning, School of Information Science, JAIST

2. Research methodology, ReaLearn (Trustworthy Lab), JAIST

3. Reading group on FAccT AI and machine learning, ReaLearn (Trustworthy Lab), JAIST

   • Purpose: is to develop research thinking in the field of Fair, Accountable, and Transparent (FAccT) machine learning

Teaching in FY 2021

1. I239E Machine Learning, School of Information Science, JAIST

2. I628E Information Processing Theory, School of Information Science, JAIST

3. Study group in answer set programming

   • Topic includes: fundamentals in answer set programming (such as Herbrand's model and the minimal model) and its connection to knowledge representation and reasoning (such as defeasible reasoning, commonsense reasoning, constraint programming, and planning problems)

4. Reading group in argumentation mining

   • Purpose: is to lead and support students, who are doing research in argument mining, to read the following book together and stimulate relevant discussions:

     • Stede, M., & Schneider, J. (2018). Argumentation Mining: Synthesis Lectures on Human Language Technologies. Morgan and Claypool.

Teaching in FY 2020

1. I239E Machine Learning, School of Information Science, JAIST

2. Study group in machine learning with ontologies

   • Topic includes: description logic, ontology, and knowledge graph; and their applications in ontology embedding

Teaching in FY 2019

1. Study group in machine learning 

   • Topics include: discriminative learning (linear regression, logistic regression, SVM), generative Learning (GDA, naive Bayes), regularization, bias/variance and practical aspects in machine learning, k-means, programming using Python and TensorFlow framework

   • Course materials are stored on J-Storage-2018: link to access the meterials.

2. Study group in argumentation 

   • Topics include: abstraction argumentation, structured argumentation, argument mining, survey of state-of-the-art techniques in the field e.g.

     • IJCAI 2016: http://www.i3s.unice.fr/~villata/tutorialIJCAI2016.html

     • ACL 2016: http://acl2016tutorial.arg.tech/

     • ACL 2019: http://arg.tech/~chris/acl2019tut/index.html