Are you working with optimization problems in economic modelling and lacking tools for finding the global optima instead of local optima? This course focuses on novel evolutionary optimization methods, such as genetic, memetic and bacterial-memetic algorithms, which are the cutting-edge methods to provide additional tools for evolutionary optimization and for finding the global optima. You will learn about these methods from Dr. Krisztián Balázs, Széchenyi István University in Győr, Hungary, and Adj. Prof. Vesa Niskanen, University of Helsinki, Finland, who has a long international career in computational intelligence.
The course provides lectures and exercises in computer environment (using Matlab, Excel and R softwares). The methods are studied both from theoretical and practical standpoints, and applied in e.g. regression and time series analysis. The course is excellent for PhD students in economics and working with especially agricultural-related research questions, but beneficial also for other research fields.
The lectures are held at the University of Helsinki Viikki Campus, but distant participation is also possible via Adobe Connection online conference system.
The traditional optimization methods have certain limitations. For example, it is typical for them that they can only provide local optima. They also often presuppose such mathematical features as continuity and differentiability for their optimizing functions. Novel evolutionary optimization methods can find the global optima in optimization. They are also more robust concerning the mathematical restrictions and thus more applicable in this respect.
In particular, the course considers such evolutionary computing methods as genetic, memetic and bacterial-memetic algorithms. In the course, we apply these methods to economic model construction and simulations in computer environment. We also use these methods within regression and time series models and cluster analysis. Hence, economical modelling is studied from both the theoretical and practical standpoints. Cognitive map modelling for examining very complex economic phenomena is also studied. Corresponding traditional mathematical and statistical methods are considered to some extent for the sake of comparison.
Prof. László Kóczy has a distinguished career in computational intelligence being also one of the leading scholars in computational intelligence and optimization with evolutionary computing. Adjunct. Prof. Vesa A. Niskanen has a long international career within computational intelligence, esp. in studies of fuzzy, neuro-fuzzy and genetic-fuzzy systems as well as in cognitive maps.
In autumn 2016 a related NOVA course “Introduction to economic modelling with computational intelligence (CI)”, arranged in the University of Helsinki, focused on computational intelligence methods. This course received positive and grateful feedback and inspired to apply for continuation. The upcoming NOVA PhD course “Novel Evolutionary Optimization Methods for Economic Modeling” can be regarded as a continuation for the previous economic modelling course and wishes welcome both new and previous students to the course.
The lectures will take place in computer class 155A in Viikki Campus at the University of Helsinki, on 11-15 December 2017, daily from 10 AM to 1 PM.
In the first two lecture days, Monday and Tuesday, Adj. Prof. Niskanen and Dr. Antti Hyvärinen will provide an overview of economical modelling applications with optimization by using traditional and certain artificial intelligence (AI) methods: fuzzy systems and neural networks.
On Wednesday and Thursday Prof. László Kóczy will briefly introduce theoretically traditional optimization methods and continue in detail with the genetic, memetic and bacterial memetic algorithms.
On Friday the contents of the course is summarized by Adj. Prof. Niskanen who will also provide guidance and instructions for drawing up the course report.
On Thursday after the lectures, the participants are welcomed to gather for the common lunch in a restaurant located in Viikki Campus. Lunch is offered by the course organizer.
Before the lectures pre-material is provided for the students for reading and introducing them to the theme. The digital material will become later available in Moodle.
For passing the course, a 5-10 pages course report should be written. In this report an economic application based on the foregoing methods is presented. These application ideas will be considered and discussed with the participants during the course, and their academic degrees are taken into account in this context. E.g. this application may deal with participant’s other studies or research work.
- highly specialised, novel, cutting-edge and multi-disciplinary knowledge on optimization in economic applications
- basic knowledge on using computational intelligence in economics
- specialised problem-solving skills for applying cutting-edge optimization and constructing computer models with computational intelligence in economics
- ability to manage and transform novel optimization and computational intelligence modelling to work or study in the contexts which are complex and require novel strategic approaches
For passing the course, an acceptable course report should be written and returned within one month from the end of the course. The report should consider a design of an application which utilizes course materials. Course is evaluated as Accepted/Failed.
The lectures are held in computer class 155A in Viikki Campus, University of Helsinki. The course is held by using mainly Matlab software (and possibly also with R and Excel), but previous knowledge of this is not required.
The course materials and further instructions are given in web-based learning environment Moodle, see the link below:
- Moodle: https://moodle.helsinki.fi/course/view.php?id=24606 (access requires university user rights)
All students outside the University of Helsinki will receive temporary user rights in order to use the computers and software (Matlab, R, Microsoft Office) in the Viikki Campus as well as Moodle during the course.
Distant participation to the course is also possible. Lectures can be followed online by using Adobe Connect conference system, which works in browser by using the link (provided in Moodle) to virtual conference room.
- 10 h independent work prior to course
- 120 h model construction and report writing (return by 14 January 2018)
- 20 h of lectures
The course is held by using mainly Matlab software (and possibly also with R and Excel), but previous knowledge of this is not required. Basic knowledge on mathematics is recommended.
Admission for NOVA courses is handled by the course organizer/ the NOVA member institution organizing the course. Students are selected to the course respect to the application order by prioritizing the NOVA-BOVA-students.
Application is open until 30 September 2017. Acceptance to the course is confirmed at latest on 11 October 2017.
To apply, please fill this e-form: https://elomake.helsinki.fi/lomakkeet/80736/lomake.html
For students outside the University of Helsinki: in order to provide user rights for the University Helsinki network during the course, please fill in and sign this form and send it by e-mail to course coordinator Eliisa Punttila: eliisa.punttila(a)helsinki.fi.
Please note, that the minimum number of students in the course is 10 and maximum number is 25. The course will not be arranged if the minimum number of students is not reached by 15 November 2017. If the course is cancelled for this reason, possible travel and accommodation expenditures are not compensated for the participants.