郑州大学电气与信息工程学院邀请Ponnuthurai Nagaratnam Suganthan教授开设进化计算课程并作学术报告，欢迎广大师生踊跃参加。
《进化计算导论》课程
带您走进自然启发的算法世界
时间：2024年07月8-12号下午2:00-4:00
地点：南核心教学区3-108
课程概览：
⟡ 10课时深入学习，掌握进化计算基础
⟡ 从自然界汲取灵感，理解遗传算法的起源与发展
⟡ 通过二进制编码，实现进化操作：交叉、变异、选择
课程亮点：
⟡ 数值优化技术，掌握差分进化与粒子群优化
⟡ 多目标进化算法，解决复杂问题的新视角
⟡ 特殊场景应用，探索约束优化与小生境策略
课程安排：
⟡ 系统讲解，理论与实践相结合
互动讨论，深化理解，激发创新思维
让我们开启进化计算的学习之旅，探索算法与自然的和谐共舞！
《学术报告》
报告一
题目：Randomization Based Deep and Shallow Learning Methods for Classification and Forecasting
时间：7月13日（周六）上午09:00-11:00
地点：电气与信息工程学院一区五楼报告厅
报告简介：
This talk will first introduce the main randomization-based feedforward learning paradigms with closed-form solutions. The popular instantiation of the randomized feedforward neural networks is called random vector functional link neural network (RVFL). Other feedforward methods included in the presentation are random weight neural networks (RWNN), extreme learning machines (ELM), Stochastic Configuration Networks (SCN), and Broad Learning Systems (BLS). We will also present deep random vector functional link implementations. Hyper-parameter tuning will be discussed. The talk will also present extensive benchmarking studies using classification and forecasting datasets.
报告二
题目：Differential Evolution with Ensembles, Adaptations and Topologies
时间：7月14日（周日）上午09:00-11:00
地点：电气与信息工程学院一区五楼报告厅
报告简介：
Differential Evolution (DE) is one of the most powerful stochastic real-parameter optimization algorithms of current interest. DE operates through similar computational steps as employed by a standard Evolutionary Algorithm (EA). However, unlike traditional EAs, the DE-variants perturb the current-generation population members with the scaled differences of distinct population members. Therefore, no separate probability distribution has to be used for generating the offspring. Since its inception in 1995, DE has drawn the attention of many researchers all over the world resulting in a lot of variants of the basic algorithm with improved performance. This talk will begin with a brief overview of the basic concepts related to numerical optimization and DE, DE’s algorithmic components and control parameters. The presentation will subsequently discuss some of the significant algorithmic variants of DE for bound constrained single-objective optimization. Recent modifications of the DE family of algorithms for constrained problems will also be included. The talk will discuss the effects of incorporating ensemble learning in DE. The talk will also discuss neighborhood topologies-based DE and adaptive DEs to improve the performance of DE.
专家简介：
Ponnuthurai Nagaratnam Suganthan，IEEE Fellow，毕业于英国剑桥大学，目前在卡塔尔大学的KINDI计算研究中心担任研究教授，他是《Swarm and Evolutionary Computation》（2010-2023年，SCI Indexed Elsevier Journal）的创始联合主编，曾担任IEEE SSCI的总主席，连续多年被Thomson Reuters Science Citation选为计算机科学领域的高被引研究者。
长期从事基于随机化的学习方法、群体与进化算法、模式识别、深度学习以及群体、进化和机器学习算法的应用。曾是《Evolutionary Computation Journal》（MIT Press，2013-2018年）的编辑委员会成员。他现/曾担任《Applied Soft Computing》、《Neurocomputing》、《IEEE Trans on Cybernetics》、《IEEE Trans on Evolutionary Computation》、《Information Sciences》、《Pattern Recognition》以及《IEEE Trans on SMC: Systems》的副主编。他是《Swarm and Evolutionary Computation》的创始联合主编，并自2024年起担任《Computers and Electrical Engineering》（SCI-indexed Elsevier journal）的联合主编。
