Sign In / Sign Out
- ASU Home
- My ASU
- Colleges & Schools
- Map & Locations
Computational intelligence encompasses a collection of fundamental research areas dealing with the creation of knowledge from data, the development of algorithms for controlling computing decisions, and the effective approaches for interfacing computers and humans. The area focuses on enhancing human decision making and learning and the automation of computing processes.
CIDSE researchers are addressing problems in automated planning and scheduling, constraint satisfaction, knowledge representation and reasoning, natural language processing, multi-agent systems, and the semantic web. Advances are being applied to robotics and other intelligent systems.
Understanding complexity and the theory of computation is critical for developing efficient algorithms. Research in this group focuses on both fundamental theory for analyzing algorithms and on developing specific deterministic and randomized algorithms for solving classic problem formulations relevant to the emerging problems in society and technology. This includes the study of complex, adaptive systems and nature-inspired approaches such as biomimicry.
As scientific and enterprise data sets grow with respect to data characteristics (volume, variety, velocity), it becomes imperative to develop new approaches to extract spatial and temporal relationships, correlation patterns and knowledge. The faculty is actively engaged in developing new scalable methods for learning with big data.
Rendering clearer images of urban scenes for games and homeland security, geometric modeling of images for new approaches to detect biosignature disease indicators using volumetric and other measures, recovery and digitization of information content in physical media and dynamic movements are all being addressed by researchers.
From universe to earth to nanoscale, random phenomena influence behavior. Models and methods are being developed to better understand and predict random behavior to allow for more efficient acquisition of knowledge (Design of Experiments), improved estimation of system reliability, better characterization of system capability and making more accurate and meaningful inferences from data.