“…In the field of neuromorphic computing, where a more “bottom-up” approach is taken to artificial intelligence, research into biological nervous systems has, as in the case of CNNs, also provided a source of architectural inspiration. This has led to models which, for example, incorporate dynamical and topological motifs inspired by the Drosophila visual, the honey-bee olfactory, honey-bee central complex, cricket auditory, and cockroach motor systems into models for motion detection (Dalgaty et al, 2018 ), contrast enhancement (Schmuker et al, 2014 ), path integration (Stone et al, 2017 ), temporal pattern detection (Sandin and Nilsson, 2020 ), and locomotion (Beer et al, 1992 ), respectively. However, such approaches have been somewhat limited by lack of an effective means of defining model parameters, whereby manual parameter tuning or correlation-based Hebbian learning rules (Hebb, 1949 ) are typically employed.…”