Abstract: A method comprising: sampling a temporal causal graph from a temporal graph distribution specifying probabilities of directed causal edges between different variables of a feature vector at a present time step, and from one variable at a preceding time step to another variables at the present time step. Based on this there are identified: a present parent which is a cause of the selected variable in the present time step, and a preceding parent which is a cause of the selected variable from the preceding time step. The method then comprises: inputting a value of each identified present and preceding parent into a respective encoder, resulting in a respective embedding of each of the present and preceding parents; combining the embeddings of the present and preceding parents, resulting in a combined embedding; inputting the combined embedding into a decoder, resulting in a reconstructed value of the selected variable.

Abstract: An exemplary embodiment provides a medical implant with implant surfaces that are exposed to body tissue when the medical implant is inserted into a body of a recipient. The implant has a micro- or a nano-sized pattern on at least a portion of the implant surfaces. Optionally, the micro- or nano-sized pattern may be a periodic (or “repeating”) pattern. Further, the micro- or nano-sized pattern may have geometric features, such as grooves, circles, triangles, rectangles, pentagons and hexagons.