I/O アイオー 1983年 NO.5 スポーツ 回路図 ベースボール ...

-->   Danilo Vasconcellos Vargas Last modified date：2024.04.25 Associate Professor / Faculty of Information Science and Electrical Engineering, Kyushu University Department of Informatics Faculty of Information Science and Electrical Engineering 1 Research Interests 2 Academic Activities 2.1 Books 2.2 Papers 2.3 Presentations 3 Membership in Academic Society 4 Educational Activities 5 Other Educational Activities 6 Professional and Outreach Activ... Graduate School Department of informatics Graduate School of Information Science and Electrical Engineering Undergraduate School Department of Electrical Engineering and Computer Science School of Engineering Other Organization Other Administration Post Other Homepage https://kyushu-u.elsevierpure.com/en/persons/danilo-vasconcellos-vargas　Reseacher Profiling Tool　Kyushu University Pure http://lis.inf.kyushu-u.ac.jp/Laboratory of Intelligent Systems (team leader) . http://danilovargas.org Academic Degree PhD Country of degree conferring institution (Overseas) Yes　Bachelor Field of Specialization Artificial General Intelligence, Cognitive Architecture, (Deep) Neural Networks, Evolutionary Computation, Global Optimization and Applications (Security, Robotics, among others). Total Priod of education and research career in the foreign country 14years00months Outline Activities (Please look at the lab's website for recent info regarding research and activities) Regarding research, I aim to develop a new generation of artificial intelligence. Additionally, I am applying the most recent artificial intelligence techniques to solve various problems in areas that range from security to electrical engineering. The results are published on top journals and conferences. In 2017, my research was published in the BBC news and in the same year my paper was published in the highest impact journal of the area of neural networks (IEEE Trans. Neural Networks). To pursue research vigorously, I am also applying to various grants. In 2018 and 2017, I was awarded three grants, including the very competitive ACT-I. In relation to education, I created two new courses (Artificial Intelligence I - Understanding the Basics and Artificial Intelligence II - Understanding the State of the Art), got accepted to present a tutorial in GECCO (which is a Core Rank A Conference) and also created a club for artificial intelligence in Kyushu University. Research Research Interests Self-Organization based Learning: Pioneering a new Paradigm in AIkeyword : Self-Organization, Artificial Intelligence2021.04～2025.04. Learning Internal Representations Robust against Adversarial Attackskeyword : Adversarial Machine Learning2020.04～2022.04. Perceptual Deep Neural Networkskeyword : Adversarial Machine Learning2020.04～2022.04. Artificial General Intelligence, Cognitive Architecture;keyword : Artificial General Intelligence2016.11～2016.11. Evolutionary Computation, Global Optimization;keyword : Evolutionary Computation2017.03～2017.03. Machine Learning, (Deep) Neural Networks, Neuroevolution;keyword : (Deep) Neural Networks2017.03～2017.03. Applications in Cybersecurity, Robotics, Economic dispatch, Brain Science, Medicine, etc.keyword : Cybersecurity, Robotics, Economic dispatch, Brain Science, Medicine,2017.03～2017.03. Academic Activities Books  Show All Books >> 1. Steven Van Uytsel, Danilo Vasconcellos Vargas, Autonomous Vehicles: Business, Technology and Law (Perspectives in Law, Business and Innovation) , Springer, 2021.01. Papers  Show All Papers >> 1. D. V. Vargas, T. Asabuki, Continual General Chunking Problem and SyncMap, AAAI 2021, 2020.12, Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills and learning of image patterns which might be a key to a more animal-like type of intelligence. Here, we propose a continual generalization of the chunking problem (an unsupervised problem), encompassing fixed and probabilistic chunks, discovery of temporal and causal structures and their continual variations. Additionally, we propose an algorithm called SyncMap that can learn and adapt to changes in the problem by creating a dynamic map which preserves the correlation between variables. Results of SyncMap suggest that the proposed algorithm learn near optimal solutions, despite the presence of many types of structures and their continual variation. When compared to Word2vec, PARSER and MRIL, SyncMap surpasses or ties with the best algorithm on 66% of the scenarios while being the second best in the remaining 34%. SyncMap's model-free simple dynamics and the absence of loss functions reveal that, perhaps surprisingly, much can be done with self-organization alone.. Presentations  Show All Presentations >> Membership in Academic Society IEEE Educational Educational Activities 2021(IUPE)Programming Practice I (IUPE)Programming Methodology Ⅰ 　Information Science (English)Hardware Experiments2020学部　情報論理学（日本語）　Information Science (English)2018, 2019学部 情報科学 [単独] (英語)大学院修士課程 Algorithms and the Law [分担]　(英語) Other Educational Activities 2020.01, Adversarial Machine Learning: On The Deeper Secrets of Deep LearningConference: IJCAI 2020(Tutorial in Top Conference). 2020.07, Adversarial Machine Learning: On The Deeper Secrets of Deep LearningConference: WCCI 2020(Tutorial in Top Conference). 2018.07, Evolutionary Reinforcement Learning: General Models and AdaptationConference: GECCO 2018(Tutorial in Top Conference). 2018.07, Introducing Learning Classifier Systems: Rules that Capture ComplexityConference: GECCO 2018(Tutorial in Top Conference). Social Professional and Outreach Activities To promote interest in AI research and development, I am creating an autonomous drone competition. I plan to create multiple projects with and/or within companies tackling SDGs. My recently created company is tackling at least 5 SDGs directly and I hope to help create much more socio-economical impact as well as a healthy entrepreneurship ecosystem.. Unauthorized reprint of the contents of this database is prohibited. Copyright © 2006, Kyushu University. All rights reserved.