Bio-Inspired Computers

• 26 hrs lectures
• 8 hrs pc labs
• 18 hrs projects

• 52 pts final exam (written part)
• 15 pts mid-term test (written part)
• 8 pts labs
• 25 pts projects

To understand the principles of bio-inspired computational systems. To be able to use the bio-inspired techniques in the design, implementation and operational phases of a computational system.
Students will be able to utilize evolutionary algorithms to design computational structures and electronic circuits. They will be able to model, simulate and implement non-conventional, in particular bio-inspired, computational systems.
Understanding the relation between computers (computing) and some natural processes.

Many phenomena observed in nature (such as evolution, self-organization and learning) can be understood as computational processes. Inspired in these phenomena, you will learn how to design algorithms and computers showing properties (such as adaptation, self-organization, energy efficiency) that are hard to achieve by means of conventional techniques developed in computer science and engineering.

• Kvasnička, V., Pospíchal J., Tiňo P.: Evolučné algoritmy. Vydavatelství STU Bratislava, 2000, 215 s., ISBN 80-227-1377-5
• Mařík et al.: Umělá inteligence IV, Academia, 2003, 480 s., ISBN 80-200-1044-0

• Sekanina L., Vašíček Z., Růžička R., Bidlo M., Jaroš J., Švenda P.: Evoluční hardware: Od automatického generování patentovatelných invencí k sebemodifikujícím se strojům. Academia Praha 2009, ISBN 978-80-200-1729-1
• Floreano D., Mattiussi C.: Bioinspired Artificial Intelligence: Theories, Methods, and Technologies. The MIT Press, Cambridge 2008, ISBN 978-0-262-06271-8
• Trefzer M., Tyrrell A.M.: Evolvable Hardware - From Practice to Application. Berlin: Springer Verlag, 2015, ISBN 978-3-662-44615-7
• Miller J.F.: Cartesian Genetic Programming, Springer Verlag, 2011, ISBN 978-3-642-17309-7
• Sze V., Chen Y.H., Yang T.J., Emer J.S.: Efficient Processing of Deep Neural Networks. Morgan & Claypool Publishers, 2020, ISBN 978-1681738352
• Rozenberg G., Bäck T., Kok J.N.: Handbook of Natural Computing, Springer 2012, 2052 p., ISBN 978-3540929093

• Banzhaf, W., Machado, P., Zhang, M.: Handbook of Evolutionary Machine Learning, Springer Singapore, 2023, 978-981-99-3813-1

1. Introduction, inspiration in biology, entropy and self-organization
2. Limits of abstract and physical computing
3. Evolutionary design
4. Cartesian genetic programming
5. Reconfigurable computing devices
6. Evolutionary design of electronic circuits
7. Evolvable hardware, applications
8. Computational development
9. Neural networks and neuroevolution
10. Neural hardware
11. DNA computing
12. Nanotechnology and molecular electronics
13. Recent trends

1. Evolutionary design of combinational circuits
2. Statistical evaluation of experiments with evolutionary design
3. Celulární automaty
4. Neuropočítače

Every student will choose one project from a list of approved projects that are relevant for this course. The implementation, presentation and documentation of the project will be evaluated. 

Mid-term exam, project and its presentation, computer lab assignments. 
Mid-term exam, realization and presentation of the project, computer lab assignments in due dates. The minimal number of points which can be obtained from the final exam is 20. Otherwise, no points will be assigned to a student. In the case of a reported barrier preventing the student to defend the project or solve a lab assignment, the student will be allowed to defend the project or solve the lab assignment on an alternative date.

None.