4.5 Article

Semantic Relatedness Emerges in Deep Convolutional Neural Networks Designed for Object Recognition

Journal

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
Volume 15, Issue -, Pages -

Publisher

FRONTIERS MEDIA SA
DOI: 10.3389/fncom.2021.625804

Keywords

deep convolutional neural network; semantic relatedness; WordNet; perceptual experience; conceptual guidance

Funding

  1. National Natural Science Foundation of China [31861143039, 31771251]
  2. National Key R&D Program of China [2019YFA0709503]
  3. National Basic Research Program of China [2018YFC0810602]

Ask authors/readers for more resources

The study reveals that deep convolutional neural networks (DCNNs) can automatically learn the semantic relatedness among objects during training, without the need for explicit top-down conceptual guidance. This relatedness is organized in a hierarchical structure and evolves into maturity throughout the training process.
Human not only can effortlessly recognize objects, but also characterize object categories into semantic concepts with a nested hierarchical structure. One dominant view is that top-down conceptual guidance is necessary to form such hierarchy. Here we challenged this idea by examining whether deep convolutional neural networks (DCNNs) could learn relations among objects purely based on bottom-up perceptual experience of objects through training for object categorization. Specifically, we explored representational similarity among objects in a typical DCNN (e.g., AlexNet), and found that representations of object categories were organized in a hierarchical fashion, suggesting that the relatedness among objects emerged automatically when learning to recognize them. Critically, the emerged relatedness of objects in the DCNN was highly similar to the WordNet in human, implying that top-down conceptual guidance may not be a prerequisite for human learning the relatedness among objects. In addition, the developmental trajectory of the relatedness among objects during training revealed that the hierarchical structure was constructed in a coarse-to-fine fashion, and evolved into maturity before the establishment of object recognition ability. Finally, the fineness of the relatedness was greatly shaped by the demand of tasks that the DCNN performed, as the higher superordinate level of object classification was, the coarser the hierarchical structure of the relatedness emerged. Taken together, our study provides the first empirical evidence that semantic relatedness of objects emerged as a by-product of object recognition in DCNNs, implying that human may acquire semantic knowledge on objects without explicit top-down conceptual guidance.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available