Statistical Relational Artificial Intelligence (StarAI) combines logical (or relational) AI and probabilistic (or statistical) AI. Relational AI deals very effectively with complex domains involving many and even a varying number of entities connected by complex relationships, while statistical AI manages well the uncertainty that derives from incomplete and noisy descriptions of the domains. Both fields achieved significant successes over the last thirty years. Relational AI laid the foundation of knowledge representation and has significantly broadened the application domain of data mining especially in bio- and chemo-informatics. It now represents some of the best-known examples of scientific discovery by AI systems in the literature. Statistical AI, in particular the use of probabilistic graphical models, has revolutionized AI, too, by exploiting probabilistic independencies. The independencies specified in such models are natural, provide structure that enables efficient reasoning and learning, and allow one to model complex domains. Many AI problems arising in a wide variety of fields such as machine learning, diagnosis, network communication, computational biology, computer vision, and robotics have been elegantly encoded and solved using probabilistic graphical models.
However, both fields evolved largely independently until about fifteen years ago, when the potential originating from their combination started to emerge. Statistical Relational Learning (SRL) was proposed for exploiting relational descriptions in statistical machine learning methods from the field of graphical models. Languages such as Markov Logic Networks, Relational Dependency Networks, PRISM, Probabilistic Relational Models, ProbLog allow the user to reason and learn with models that describe complex and uncertain relationships among domain entities.
Meanwhile, the scope of SRL was significantly advanced in StarAI to cover all forms of reasoning and models of AI. StarAI is nowadays an ample area encompassing many and diverse approaches. One major example is given by neural-symbolic paradigms, that address the long-standing problem of combining symbolic and connectionist approaches for knowledge representation, learning and reasoning, with new impulse coming from the area of deep learning.
The goal of this Research Topic in the Computational Intelligence specialty section of Frontiers in Robotics and AI is to collect articles providing a picture of the current status and trends of StarAI. We are also organizing a summer school to be held in 2018 on StarAI and we plan to invite selected authors of papers from the Research Topic to give lectures in the school.
The non-exhaustive list of topics of interest for this Research Topic is:
- Representation languages
- Inference algorithms
- Lifted inference
- Learning algorithms
- Complexity analyses
- Tractable languages
- Algorithm scaling
- Theoretical frameworks
- Probabilistic Programming
- Optimization
- Neural-symbolic paradigms
- Deep neural architectures for knowledge representation and reasoning
Statistical Relational Artificial Intelligence (StarAI) combines logical (or relational) AI and probabilistic (or statistical) AI. Relational AI deals very effectively with complex domains involving many and even a varying number of entities connected by complex relationships, while statistical AI manages well the uncertainty that derives from incomplete and noisy descriptions of the domains. Both fields achieved significant successes over the last thirty years. Relational AI laid the foundation of knowledge representation and has significantly broadened the application domain of data mining especially in bio- and chemo-informatics. It now represents some of the best-known examples of scientific discovery by AI systems in the literature. Statistical AI, in particular the use of probabilistic graphical models, has revolutionized AI, too, by exploiting probabilistic independencies. The independencies specified in such models are natural, provide structure that enables efficient reasoning and learning, and allow one to model complex domains. Many AI problems arising in a wide variety of fields such as machine learning, diagnosis, network communication, computational biology, computer vision, and robotics have been elegantly encoded and solved using probabilistic graphical models.
However, both fields evolved largely independently until about fifteen years ago, when the potential originating from their combination started to emerge. Statistical Relational Learning (SRL) was proposed for exploiting relational descriptions in statistical machine learning methods from the field of graphical models. Languages such as Markov Logic Networks, Relational Dependency Networks, PRISM, Probabilistic Relational Models, ProbLog allow the user to reason and learn with models that describe complex and uncertain relationships among domain entities.
Meanwhile, the scope of SRL was significantly advanced in StarAI to cover all forms of reasoning and models of AI. StarAI is nowadays an ample area encompassing many and diverse approaches. One major example is given by neural-symbolic paradigms, that address the long-standing problem of combining symbolic and connectionist approaches for knowledge representation, learning and reasoning, with new impulse coming from the area of deep learning.
The goal of this Research Topic in the Computational Intelligence specialty section of Frontiers in Robotics and AI is to collect articles providing a picture of the current status and trends of StarAI. We are also organizing a summer school to be held in 2018 on StarAI and we plan to invite selected authors of papers from the Research Topic to give lectures in the school.
The non-exhaustive list of topics of interest for this Research Topic is:
- Representation languages
- Inference algorithms
- Lifted inference
- Learning algorithms
- Complexity analyses
- Tractable languages
- Algorithm scaling
- Theoretical frameworks
- Probabilistic Programming
- Optimization
- Neural-symbolic paradigms
- Deep neural architectures for knowledge representation and reasoning