The KISS project is investigating new development tools to improve AI-based algorithms in signal processing and how to use computers to convert them into highly efficient implementations. The resulting reduction in development times promises improved or even completely new products and services for mobility, communication and entertainment. »KISS« is the German abbreviation which corresponds to »Laboratory for system level design of machine learning based signal processing applications«.
All the research findings are being passed on to all relevant interested parties by means of university teaching and training in industry. This includes both the generation of training data as well as the efficient implementation and optimization of systems consisting of different computing units such as graphics cards or programmable chips. Combining traditional and machine learning methods increases the algorithms’ applicability and lowers the barriers to entry for industrial companies.
To achieve these goals, the algorithms to be applied are modeled with a high level of abstraction in form of semantic models, which can then be optimized using computers and transferred to different target platforms. The project team also provides concepts for how to obtain training data from existing data pools and simulation environments. To ensure that these methods are suited for practical use, they are tested on various video, speech and audio applications, for instance optical environment detection or the improvement of the acoustic human-machine interface.
The research findings will serve two purposes: one, they will feed into the training and education measures that will be offered as well as into scientific publications; and two, there are plans for R&D services and licensing based on the methods and tools developed.
KISS is a joint project of Fraunhofer IIS and the Friedrich-Alexander-Universität Erlangen-Nürnberg. Further information about the project and on the topic of artificial intelligence can be found here.