Related Experiment Video
Updated: Nov 14, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
769
Semantic Relatedness Emerges in Deep Convolutional Neural Networks Designed for Object Recognition
Taicheng Huang1, Zonglei Zhen2, Jia Liu3
1State Key Laboratory of Cognitive Neuroscience and Learning and IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing, China.
Frontiers in Computational Neuroscience
|March 11, 2021
Summary
Deep convolutional neural networks (DCNNs) learned object category relationships hierarchically, mimicking human semantic structures. This suggests conceptual guidance isn't essential for learning object relatedness.
Area of Science:
- Cognitive Science
- Artificial Intelligence
- Neuroscience
Background:
- Humans possess a hierarchical semantic understanding of object categories.
- A dominant theory posits top-down conceptual guidance is crucial for forming this hierarchy.
Purpose of the Study:
- To investigate if deep convolutional neural networks (DCNNs) can learn object relationships bottom-up.
- To challenge the necessity of top-down conceptual guidance in hierarchical learning.
Main Methods:
- Analyzing representational similarity in a DCNN (AlexNet) trained for object categorization.
- Comparing DCNN-derived object relatedness with human semantic networks (WordNet).
Main Results:
- DCNNs spontaneously organized object categories hierarchically.
- This emerged hierarchy closely resembled human semantic relatedness.
- Hierarchical structure developed progressively (coarse-to-fine) and preceded recognition ability.
- Task demands influenced the fineness of the learned hierarchy.
Conclusions:
- Semantic relatedness can emerge as a byproduct of object recognition in DCNNs.
- This implies humans may acquire semantic knowledge without explicit top-down conceptual input.
Related Concept Videos
01:24Natural and Artificial Concepts
378
In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint...
378
01:26Causes of Similarity-Dissimilarity Effect
107
The similarity-dissimilarity effect, a fundamental concept in social psychology, explains how interpersonal similarities and differences influence attraction and social interactions. This effect is supported by three key psychological perspectives: balance theory, social comparison theory, and consensual validation.Balance Theory and Cognitive ConsistencyBalance theory, developed by Fritz Heider, posits that individuals seek cognitive consistency in their relationships. When two people share...
107
01:25Neural Circuits
2.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.1K
01:27Associative Learning
836
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
836
01:20Parallel Processing
429
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
429
01:22Force Classification
2.0K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.0K