Ayzenberg et al. describe how principles from child development can be used to improve the capacities and biological plausibility of AI models. These principles can be incorporated into every stage of the modeling process, from the architectures to the benchmarks.

Ayzenberg and Arcaro characterize the functional organization of the human visual system at birth and across the last trimester of gestation. They find that the neonate visual system can already be segregated into three hierarchically organized visual pathways: ventral, lateral, and dorsal. They also find developmental differences between pathways, with the dorsal visual pathway being more mature than the others.

Background The human visual system is full of optimisations—mechanisms designed to extract the most useful information from a constant stream of incoming data. The field of neuro-AI has made significa...

In response to the opinion article by Cusack et al. [1], Zettersten et al. [2] challenge the proposal that human infants undergo a stage-like development from sensory to goal-directed actions. Zetters...