イベント

開催内容

第7回 神戸大学CMDS先端セミナー

タイトル

Spatiotemporal Graph Neural Networks

講演者

Prof. Cesare Alippi (Professor of Information Processing Systems, Politecnico di Milano)

日時

2024年7月11日(木) 15:00 - 16:00

場所

六甲台第２キャンパス 工学部　C4-301

形式

ハイブリッド　※できるだけ対面参加をお願いします。
参加 Zoom ミーティング
https://kobe-u-ac-jp.zoom.us/j/87310928570?pwd=VkJLNVncrV1nKGe4aaozBEZuxUbAoc.1
ミーティング ID: 873 1092 8570　　パスコード: 395147

概要

Machine learning research on graph-based structured data is booming, with thousands of papers released in the past years. The increased production does not only shows the interest in foundational research but the relevance in applications too, as graphs with their information entities and relational dependencies are everywhere. The seminar will open views on spatiotemporal neural graph processing, i.e., in research/application frameworks where, in addition to “space” relations we exploit those that emerge over the time dimension. Applications enabling such processing are e.g., those associated with sensor networks in domains nowadays named smart grids, smart cities, IoT, Industry 40. The focus will mostly be on the prediction and the imputation tasks within a deep relational processing.

略歴

CESARE ALIPPI received the degree in electronic engineering cum laude in 1990 and the PhD in 1995 from Politecnico di Milano, Italy. Currently, he is a Professor with the Politecnico di Milano, Milano, Italy and Università della Svizzera italiana, Lugano, Switzerland. He has been a visiting researcher at UCL (UK), MIT (USA), ESPCI (F), CASIA (RC), A*STAR (SIN), GDUT (RC). Alippi is an IEEE Fellow, an ELLIS Fellow and an AAIA Fellow, Past Board of Governors member of the International Neural Network Society, past Vice-President education and Administrative Committee member of the IEEE Computational Intelligence Society, past associate editor of the IEEE Transactions on Emerging topics in computational intelligence, the IEEE Computational Intelligence Magazine, the IEEE-Transactions on Instrumentation and Measurements, the IEEE-Transactions on Neural Networks. He received the 2024 IEEE CIS Enrique Ruspini Meritorious Award, 2018 IEEE CIS Outstanding Computational Intelligence Magazine Award, the 2016 Gabor award from the International Neural Networks Society and the 2013 IEEE CIS Outstanding Transactions on Neural Networks and Learning Systems Paper Award, the IBM Faculty award, the 2004 IEEE Instrumentation and Measurement Society Young Engineer Award. Current research activity addresses graph processing, intelligence for embedded IoT, adaptation and learning in non-stationary environments and cyber-physical systems. He holds 8 patents, has published one monograph book, 7 edited books and more than 250 papers in international journals and conference proceedings.

第6回 神戸大学CMDS先端セミナー

タイトル

The State of the Art of Collaborative Neurodynamic Optimization

講演者

Prof. Jun Wang (Department of Computer Science & School of Data Science, City University of Hong Kong)

日時

2024年5月27日（月）　15:00-16:00

場所

工学研究科 LR-402 教室

概要

The past four decades witnessed the birth and growth of neurodynamic optimization, which has emerged as a potentially powerful problem-solving tool for constrained optimization due to its inherent nature of biological plausibility and parallel and distributed information processing. Despite the success, almost all existing neurodynamic approaches a few years ago worked well only for optimization problems with convex or generalized convex functions. Effective neurodynamic approaches to optimization problems with nonconvex functions and discrete variables are rarely available. In this talk, the advances in neurodynamic optimization will be presented. Specifically, In the proposed collaborative neurodynamic optimization framework, multiple neurodynamic optimization models with different initial states are employed for scattered searches. In addition, a meta-heuristic rule in swarm intelligence (such as PSO) is used to reposition neuronal searches upon their local convergence to escape local minima toward global optima. Problem formulations and experimental results will be elaborated to substantiate the viability and efficacy of several specific paradigms in this framework for supervised/semi-supervised feature selection, supervised learning, vehicle-task assignment, model predictive control, energy load dispatching, and financial portfolio selection.

開催報告

【講演概要】
香港城市大学のJun Wang教授に動的ニューラルネットによる協調型最適化手法の最新動向について、ご講演頂きました。まず、人の脳で行われている最適化の仕組みがフィードバック結合を有するニューラルネットの動的な特性を利用していることについて述べられ、そのパイオニアとしてJohn J. Hopfieldを紹介されました。そして、最適化問題の種類やその解法、特に非線形最適化問題を解くためのニューラルネットモデルと最適化問題への定式化、収束条件などを説明され、本講演の中心となるCollaborative Neurodynamicsの概念について詳細な説明がありました。

【発表形式】ハイブリッド（対面＋オンライン）
【参加者】教員・学生 44名（対面参加者15名、オンライン参加者29名）
【担当者】小澤誠一（数理・データサイエンスセンター）

第１回～第５回は，2018年度，2019年度のイベント履歴をご覧ください

問い合わせ先
こちらをご参照ください。