English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Convolutional neural network (CNN), as an important model in artificialintelligence, has been widely used and studied in different disciplines. Thecomputational mechanisms of CNNs are still not fully revealed due to the theircomplex nature. In this study, we focused on 4 extensively studied CNNs(AlexNet, VGG11, VGG13, and VGG16) which has been analyzed as human-like modelsby neuroscientists with ample evidence. We trained these CNNs to emotionvalence classification task by transfer learning. Comparing their performancewith human data, the data unveiled that these CNNs would partly perform ashuman does. We then update the object-based AlexNet using self-attentionmechanism based on neuroscience and behavioral data. The updated FE-AlexNetoutperformed all the other tested CNNs and closely resembles human perception.The results further unveil the computational mechanisms of these CNNs.Moreover, this study offers a new paradigm to better understand and improve CNNperformance via human data.

Using Human-like Mechanism to Weaken Effect of Pre-training Weight Bias in Face-Recognition Convolutional Neural Network