Module also offered within study programmes:
General information:
Name:
Bio-Inspired Artificial Intelligence
Course of study:
2019/2020
Code:
ZSDA-3-0106-s
Faculty of:
Szkoła Doktorska AGH
Study level:
Third-cycle studies
Specialty:
-
Field of study:
Szkoła Doktorska AGH
Semester:
0
Profile of education:
Academic (A)
Lecture language:
English
Form and type of study:
Full-time studies
Course homepage:
Responsible teacher:
dr hab. inż. Dreżewski Rafał (drezew@agh.edu.pl)
Dyscypliny:
automatyka, elektronika i elektrotechnika, informatyka, informatyka techniczna i telekomunikacja, inżynieria biomedyczna, nauki o zarządzaniu i jakości
Module summary

The course acquaints the student with modern bio-inspired artificial intelligence algorithms, including open research questions and future research directions. The student learns current research methods in bio-inspired AI and develops the ability to independently and creatively solve encountered research problems during the realization of a research project. Also, the ability to write scientific papers and present research results is developed during the classes.

Description of learning outcomes for module
MLO code Student after module completion has the knowledge/ knows how to/is able to Connections with FLO Method of learning outcomes verification (form of completion)
Social competence: is able to
M_K001 The student is able to critically asses non-technical aspects and consequences of the applications of bio-inspired artificial intelligence algorithms. SDA3A_K02, SDA3A_K01, SDA3A_K03 Scientific paper,
Project,
Presentation,
Participation in a discussion,
Involvement in teamwork,
Execution of a project,
Activity during classes
Skills: he can
M_U001 The student can identify open research problems in the area of bio-inspired artificial intelligence and solve them carrying out the research. SDA3A_U07, SDA3A_U06, SDA3A_U01 Scientific paper,
Project,
Presentation,
Participation in a discussion,
Execution of a project,
Activity during classes
M_U002 The student can develop and implement modern bio-inspired artificial intelligence algorithms using selected programming tools and libraries. SDA3A_U07, SDA3A_U06, SDA3A_U02, SDA3A_U05, SDA3A_U01 Involvement in teamwork,
Project,
Execution of a project,
Activity during classes
M_U003 The student can carry out experiments using the developed bio-inspired artificial intelligence algorithms. SDA3A_U06, SDA3A_U01 Project,
Involvement in teamwork,
Execution of a project,
Activity during classes
M_U004 The student can analyze and interpret the results of experiments performed with the use of developed bio-inspired artificial intelligence algorithms. SDA3A_U01 Scientific paper,
Project,
Execution of a project,
Activity during classes
M_U005 The student can write a scientific paper presenting the performed research in the area of bio-inspired artificial intelligence algorithms. SDA3A_U02, SDA3A_U03, SDA3A_U05, SDA3A_U01, SDA3A_U04 Scientific paper,
Execution of a project,
Activity during classes
M_U006 The student can prepare a presentation showing the most important outcomes of the performed research. SDA3A_U02, SDA3A_U03, SDA3A_U05, SDA3A_U04 Project,
Presentation,
Participation in a discussion,
Execution of a project,
Activity during classes
Knowledge: he knows and understands
M_W001 The student knows and understands modern bio-inspired artificial intelligence algorithms. SDA3A_W03, SDA3A_W04, SDA3A_W01, SDA3A_W02 Project,
Scientific paper,
Presentation,
Participation in a discussion,
Execution of a project,
Activity during classes
M_W002 The student knows and understands open research questions and future research directions in the area of bio-inspired artificial intelligence. SDA3A_W03, SDA3A_W05, SDA3A_W01, SDA3A_W02 Scientific paper,
Project,
Presentation,
Participation in a discussion,
Execution of a project,
Activity during classes
M_W003 The student knows and understands possible areas of real-life applications of bio-inspired artificial intelligence algorithms. SDA3A_W03, SDA3A_W07, SDA3A_W05, SDA3A_W04, SDA3A_W06 Scientific paper,
Project,
Participation in a discussion,
Execution of a project,
Activity during classes
Number of hours for each form of classes:
Sum (hours)
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Prace kontr. przejść.
Lektorat
60 10 0 0 30 0 20 0 0 0 0 0
FLO matrix in relation to forms of classes
MLO code Student after module completion has the knowledge/ knows how to/is able to Form of classes
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Prace kontr. przejść.
Lektorat
Social competence
M_K001 The student is able to critically asses non-technical aspects and consequences of the applications of bio-inspired artificial intelligence algorithms. + - - + - + - - - - -
Skills
M_U001 The student can identify open research problems in the area of bio-inspired artificial intelligence and solve them carrying out the research. - - - + - - - - - - -
M_U002 The student can develop and implement modern bio-inspired artificial intelligence algorithms using selected programming tools and libraries. - - - + - - - - - - -
M_U003 The student can carry out experiments using the developed bio-inspired artificial intelligence algorithms. - - - + - - - - - - -
M_U004 The student can analyze and interpret the results of experiments performed with the use of developed bio-inspired artificial intelligence algorithms. - - - + - - - - - - -
M_U005 The student can write a scientific paper presenting the performed research in the area of bio-inspired artificial intelligence algorithms. - - - + - - - - - - -
M_U006 The student can prepare a presentation showing the most important outcomes of the performed research. - - - - - + - - - - -
Knowledge
M_W001 The student knows and understands modern bio-inspired artificial intelligence algorithms. + - - + - + - - - - -
M_W002 The student knows and understands open research questions and future research directions in the area of bio-inspired artificial intelligence. + - - + - + - - - - -
M_W003 The student knows and understands possible areas of real-life applications of bio-inspired artificial intelligence algorithms. + - - + - + - - - - -
Student workload (ECTS credits balance)
Student activity form Student workload
Summary student workload 180 h
Module ECTS credits 6 ECTS
Udział w zajęciach dydaktycznych/praktyka 60 h
Preparation for classes 35 h
przygotowanie projektu, prezentacji, pracy pisemnej, sprawozdania 50 h
Realization of independently performed tasks 30 h
Contact hours 5 h
Module content
Lectures (10h):

  1. Introduction to the bio-inspired artificial intelligence – its origins and possible future.
  2. Evolutionary algorithms – from evolutionary biology to evolutionary AI.
  3. Co-evolutionary algorithms – AI resulting from intra- and inter-species interactions.
  4. Speciation algorithms – using species formation processes to obtain intelligent behavior.
  5. Multi-modal and multi(many)-objective evolutionary algorithms – applications in real-life problems.
  6. Agent-based evolution – making the evolutionary AI more realistic.
  7. Open research questions and future research directions and trends in bio-inspired AI.

Project classes (30h):

  1. Development and implementation of innovative or known from the literature bio-inspired AI algorithm.
  2. Conducting preliminary experiments using the implemented bio-inspired AI algorithm. Verification of the correctness of the results and tuning the algorithm. Possible modification of the algorithm and further experiments.
  3. Conducting target experiments using the implemented algorithm.
  4. Analysis and interpretation of the obtained experimental results.
  5. Preparation of a scientific publication based on the results of the conducted research.

Seminar classes (20h):

Students analyze, present and discuss modern bio-inspired AI approaches and algorithms, including open research questions and problems. The exemplary research areas subjected to analysis and discussion during classes include:

  1. Differential Evolution.
  2. Swarm Intelligence.
  3. Ant colony optimization.
  4. Particle Swarm Optimization.
  5. Memetic algorithms.
  6. Cultural algorithms.
  7. Hybrid evolutionary algorithms.
  8. Agent-based evolutionary approaches.
  9. Novel bio-inspired algorithms.

Additional information
Teaching methods and techniques:
  • Lectures: The content of the lecture is presented in the form of a multimedia presentation in combination with a traditional blackboard lecture enriched with discussions with the audience related to the presented open research issues.
  • Project classes: Students carry out a given project themselves, consulting the encountered problems with the teacher, however, without any significant interference on his part. The goal is to become acquainted with current research methods and techniques and to develop the ability to independently and creatively solve encountered research problems. The aim of the classes is also to develop the ability to write scientific papers.
  • Seminar classes: Students analyze, present, and discuss modern algorithms and methods of bio-inspired artificial intelligence, also the open research problems in that area. The goal is to become acquainted with current trends and research directions in the field of bio-inspired AI and to develop the ability to analyze and discuss the results of scientific research critically.
Warunki i sposób zaliczenia poszczególnych form zajęć, w tym zasady zaliczeń poprawkowych, a także warunki dopuszczenia do egzaminu:
  1. Lectures: realization of the research project, preparation of a scientific publication, and active participation in the seminars.
  2. Project classes: realization of the research project and preparation of a scientific publication based on the results of carried out research.
  3. Seminar classes: presentation of selected research topics in the area of bio-inspired AI and active participation in discussions.
Participation rules in classes:
  • Lectures:
    – Attendance is mandatory: No
    – Participation rules in classes: Students take part actively in classes and acquire knowledge in the field of bio-inspired artificial intelligence, according to the plan of lectures. Students should keep asking questions and clarifying doubts during the lectures. Audiovisual registration of the lecture requires the lecturer's consent.
  • Project classes:
    – Attendance is mandatory: Yes
    – Participation rules in classes: Students carry out a project aimed at the development and implementation of innovative or selected from the literature bio-inspired artificial intelligence algorithm, conducting experiments, and analyzing their results. The method of project realization and the final results described in the scientific publication are assessed.
  • Seminar classes:
    – Attendance is mandatory: Yes
    – Participation rules in classes: Students actively participate in seminars, presenting, analyzing, and discussing current research trends, directions, and problems in the field of bio-inspired artificial intelligence.
Method of calculating the final grade:

The final grade is calculated in the following way:
0.3 * development and implementation of the selected bio-inspired AI algorithm + 0.15 * conducting experimental research and analysis and interpretation of the experimental results + 0.3 * preparation of a scientific publication describing the developed AI algorithm and conducted experiments + 0.25 * presentation of the selected research topics in the area of bio-inspired AI and participation in the discussions on open research issues during the seminar classes.

Sposób i tryb wyrównywania zaległości powstałych wskutek nieobecności studenta na zajęciach:

The way of clearing backlogs resulting from the student’s absence during classes includes carrying out a project on the subject set with the teacher and preparation of the scientific paper based on the performed research.

Prerequisites and additional requirements:

Students should know the basics of artificial intelligence methods (at the level of engineering or MSc studies). Also, the students should be able to write programs in Java/Scala/Python/C++ or another programming language in which it is possible to implement a selected bio-inspired AI algorithm. The basic knowledge of statistical methods and tools (for example, R language) is also required.

Recommended literature and teaching resources:
  1. Floreano D., Mattiussi C., Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies, The MIT Press, 2008.
  2. Pétrowski A., Ben-Hamida S., Evolutionary Algorithms, ISTE Ltd and John Wiley & Sons, London, UK and Hoboken, USA, 2017.
  3. Simon D., Evolutionary Optimization Algorithms, John Wiley & Sons, Inc., Hoboken, New Jersey, 2013.
  4. Price K. V., Storn R. M., Lampinen J. A., Differential Evolution. A Practical Approach to Global Optimization, Springer-Verlag, Berlin Heidelberg, 2005.
  5. Russell S., Norvig P., Artificial Intelligence: A Modern Approach, Pearson, 2010.
  6. Wooldridge M., An Introduction to MultiAgent Systems, Wiley, 2009.
  7. Ferber J., Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence, Addison-Wesley, 1999.
  8. Sarker R.A., Ray T., (ed.), Agent-Based Evolutionary Search, Springer, 2010.
  9. Engelbrecht A.P., Fundamentals of Computational Swarm Intelligence, Wiley, 2005.
  10. Dorigo M., Stützle T., Ant Colony Optimization, The MIT Press, 2004.
  11. Lee R.S.T. (ed.), Computational Intelligence for Agent-based Systems, Springer-Verlag, 2007.
Scientific publications of module course instructors related to the topic of the module:
  1. R. Dreżewski, S. Kruk, and M. Makówka. The evolutionary optimization of a company’s return on equity factor: Towards the agent-based bio-inspired system supporting corporate finance decisions. IEEE Access, 6:51911–51930, 2018.
  2. R. Dreżewski and M. Klęczar. Artificial intelligence techniques for the Puerto Rico strategy game. In G. Jezic, M. Kusek, Y.-H. J. Chen-Burger, R. J. Howlett, and L. C. Jain, editors, Agent and Multi-Agent Systems: Technology and Applications. 11th KES International Conference, KES-AMSTA 2017 Vilamoura, Algarve, Portugal, June 2017 Proceedings, volume 74 of Smart Innovation, Systems and Technologies, pages 77-87. Springer International Publishing, 2018
  3. R. Dreżewski and K. Doroz. An agent-based co-evolutionary multi-objective algorithm for portfolio optimization. Symmetry, 9(9):168, 2017.
  4. L. Siwik and R. Dreżewski. Hierarchical and massively interactive approaches for hybridization of evolutionary computations and agent systems-comparison in financial application. In Leszek Rutkowski, Marcin Korytkowski, Rafał Scherer, Ryszard Tadeusiewicz, Lotfi A. Zadeh, and Jacek M. Zurada, editors, Artificial Intelligence and Soft Computing. 15th International Conference, ICAISC 2016, Zakopane, Poland, June 12-16, 2016, Proceedings, Part I, volume 9692 of Lecture Notes in Computer Science, pages 505-516. Springer International Publishing, 2016
  5. R. Dreżewski, K. Cetnarowicz, G. Dziuban, S. Martynuska, and A. Byrski. Agent-based neuro-evolution algorithm. In G. Jezic, R. J. Howlett, and L. C. Jain, editors, Agent and Multi-Agent Systems: Technologies and Applications. 9th KES International Conference, KES-AMSTA 2015 Sorrento, Italy, June 2015, Proceedings, volume 38 of Smart Innovation, Systems and Technologies, pages 95-108. Springer International Publishing, 2015.
  6. A. Byrski, R. Dreżewski, L. Siwik, and M. Kisiel-Dorohinicki. Evolutionary multi-agent systems. The Knowledge Engineering Review, 30(2):171-186, 2015.
Additional information:

-