Making neural networks more neural

Deep neural networks (DNNs) are practical and effective but, despite the name, they lack biological validity. The recent study by Kang et al.¹ in <i>Patterns</i> takes a step toward rectifying this deficit by hard-wiring receptive fields into the first layer of a visual DNN, and the authors show that their network can generalize across image types. Training on photographs, for example, resulted in good performance on sketches; conventional DNNs did not match this behavior.