Course details
Evolutionary and Neural Hardware
EUD Acad. year 2019/2020 Summer semester
This course introduces selected computational models and computer systems which have appeared at the intersection of hardware and artificial intelligence in order to address insufficient performance and energy efficiency of conventional computers for solving some hard problems. The course surveys relevant theoretical models, circuit techniques and computational intelligence methods inspired in biology. In particular, the following topics will be discussed: evolutionary design, evolvable hardware, neural hardware, DNA computing and approximate computing. Typical applications will illustrate these approaches..
Guarantor
Language of instruction
Completion
Time span
- 26 hrs lectures
Assessment points
- 100 pts final exam
Department
Lecturer
Instructor
Subject specific learning outcomes and competences
Students will be able to utilize evolutionary algorithms to design electronic circuits. They will be able to model, simulate and implement bio-inspired computational systems, particularly evolvable and neural hardware.
Understanding the relation between computers (computing) and some natural processes.
Learning objectives
To understand the principles of bio-inspired computing techniques and their use particularly during the design, hardware implementation and operation of computer systems.
Study literature
- 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
- Reda S., Shafique M.: Approximate Circuits - Methodologies and CAD. Springer Nature, 2019, ISBN 978-3-319-99322-5
- Sekanina L., Vašíček Z., Růžička R., Bidlo M., Jaroš J., Švenda P.: Evoluční hardware: Od automatického generování patentovatelných invencí k sebemodifikujícím se strojům (http://www.academia.cz/evolucni-hardware.html). Academia Praha 2009, ISBN 978-80-200-1729-1
Syllabus of lectures
- Introduction
- Bio-inspired computational models (inspiration, principles of adaptation and self-organization)
- Approximate computing and energy efficiency
- Hardware and reconfigurable devices for artificial intelligence
- Evolutionary design
- Cartesian genetic programming
- Evolutionary design of digital and analogue circuits
- Scalability problems of evolutionary design
- Computational development, cellular automata, L-systems
- Deep neural networks and their hardware implementation
- Approximate computing for neural networks
- DNA computing
- Recent HW/SW platforms and applications
Controlled instruction
Elaboration and presentation of a project.
Course inclusion in study plans