It searches for the most beautiful snapshots from our image masses, evaluates complex sensor data in vehicles, enables ever better forecasts for feed-in from renewable energies and increases efficiency in production processes. OFFIS researches and develops AI-based solutions for current and future challenges in the fields of health, transport, energy and production in a digitized world of life and work that depends on the smooth functioning of increasingly complex infrastructures. The collective term "artificial intelligence" refers in particular to methods and procedures from machine learning and distributed, autonomous and learning systems.
Deep learning is the field of machine learning that focuses on so-called "deep" neural networks. For some years now Deep Learning has been showing a rapid development with astonishing success: From facial and speech recognition, which has found its way into our mobile phones, to learning complex strategies at AlphaGo Zero, Deep Learning has become an important discipline in science and applied research. In order to bundle the methodical competences and strategic developments in applied research in the fields of health, energy, transport and production, the OFFIS Competence Cluster Deep Learning was established. In close cooperation with the Computation Intelligence working group of the Carl von Ossietzky University of Oldenburg, regular lectures are organized and further education is offered for industry and commerce. You can find more information and contact details on the website of the Competence Cluster Deep Learning.
Distributed artificial intelligence is defined as (partially) autonomous hardware and software systems that cooperate with each other to solve problems that cannot be solved by individual components. These so-called agents usually have an individual intelligence for monitoring and controlling technical processes, are able to communicate with other agents and are able to flexibly train different organizational forms depending on the situation. Under the heading "Self-organization" OFFIS works especially on nature-inspired methods for heuristic optimization in complex systems like energy supply. The research work focuses on the agent-based self-organization of cyber-resilient smart grids, which stabilize themselves independently in the event of malfunctions and can rebuild the supply independently in the event of a blackout. In addition, OFFIS has been investigating energy-economical aspects such as the self-organized aggregation and marketing of the flexibility of decentralized energy plants in the context of virtual power plants for many years.
IT system components and mechanical or electronic system components interact in cyber-physical systems (CPS for short). Today, complex CPS can be found in practically every area of life: from vehicles with modern assistance systems to industrial process control and automation to digitized energy systems, IT components are taking on increasingly important tasks in safety-relevant applications. The use of AI plays an important role, since classical algorithms are no longer able to realize complex functions in these highly dynamic environments. When using AI especially in safety-relevant CPS, however, only inadequately answered questions arise: How can a correct functioning of an AI be guaranteed? How can decisions of AI-based systems be made transparent and comprehensible? Can AI also help to identify systemic vulnerabilities in security-relevant CPS? OFFIS pursues these research questions in the Competence Clusters Safety Relevant Cyber Physical Systems and Deep Learning, bringing together proven expertise in the analysis and design of safety-critical systems and sound methodological knowledge in machine learning.
Dominik Filipiak, Milena Strozyna, Krzystof Wecel, Matthias Steidel, Witold Abramowicz; Oktober / 2020