We offer a postdoctoral researcher position within the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence at the University of Groningen, The Netherlands. The position is funded by an NWO Vidi project named “mechanistic machine learning: combining the explanatory power of dynamic models with the predictive power of machine learning“. Systems of Artificial Intelligence (AI) and Machine Learning (ML) gained a tremendous amount of interest in recent years, demonstrating great performance for a wide variety of tasks, but typically only if they are trained on huge amounts of data. Moreover, frequently no insight into the decision making is available or required. Experts desire to know how their data can inform them about the natural processes being measured. Therefore we develop transparent and interpretable model- and data-driven hybrid methods that are demonstrated for applications in medicine and engineering. As a postdoc, you will work together with Kerstin Bunte and her team within the Intelligent Systems group, as well as a network of interdisciplinary collaborators in the UK and Europe from various fields, such as Computer Science, Engineering and Applied Mathematics.

In recent years it has become increasingly clear that (Shannon) information is a central resource for organisms, akin in importance to energy. Any decision that an organism or a subsystem of an organism takes involves the acquisition, selection, and processing of information and ultimately its concentration and enaction. It is the consequences of this balance that will occupy us in this talk. This perception-action loop picture of an agent's life cycle is well established and expounded especially in the context of Fuster's sensorimotor hierarchies. Nevertheless, the information-theoretic perspective drastically expands the potential and predictive power of the perception-action loop perspective. On the one hand information can be treated - to a significant extent - as a resource that is being sought and utilized by an organism. On the other hand, unlike energy, information is not additive. The intrinsic structure and dynamics of information can be exceedingly complex and subtle; in the last two decades one has discovered that Shannon information possesses a rich and nontrivial intrinsic structure that must be taken into account when informational contributions, information flow or causal interactions of processes are investigated, whether in the brain or in other complex processes. In addition, strong parallels between information and control theory have emerged. This parallelism between the theories allows one to obtain unexpected insights into the nature and properties of the perception-action loop. Through the lens of information theory, one can not only come up with novel hypotheses about necessary conditions for the organization of information processing in a brain, but also with constructive conjectures and predictions about what behaviours, brain structure and dynamics and even evolutionary pressures one can expect to operate on biological organisms, induced purely by informational considerations.