Making neural networks more neural.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41726094.
- Also identified by DOI 10.1016/j.patter.2026.101494 and PMC identifier 12921498.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
Deep neural networks (DNNs) are practical and effective but, despite the name, they lack biological validity. The recent study by Kang et al.<sup>1</sup> 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.