深度神经网络与人类的代表性对齐的基础维度
Florian P Mahner1,2, Lukas Muttenthaler1,3,4, Umut Güçlü2
1Vision and Computational Cognition Group, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany.
Nature machine intelligence
|June 26, 2025
概括
通过比较人类和人工智能 (AI) 的表现,可以发现关键差异. 一个新的框架显示,与人类不同,深度神经网络 (DNN) 优先考虑视觉而不是语义属性,突出了人工智能与人类代表性对齐的挑战.
科学领域:
- 计算认知神经科学 计算认知神经科学
- 机器学习 机器学习
- 人工智能 (AI) 研究研究
背景情况:
- 了解人类认知和开发可靠的人工智能是关键目标.
- 以前的AI-人类代表性比较使用了全球指标,限制了对对齐因素的洞察力.
- 需要方法来直接比较代表性策略.
研究的目的:
- 引入一个新的框架来比较人类和人工智能表示.
- 识别潜在的表征维度,是人类和人工智能的基本行为.
- 揭示人类和深度神经网络 (DNN) 之间的图像处理策略的差异.
主要方法:
- 开发了一个通用的框架来识别潜在的表示维度.
- 应用框架来比较人类参与者和处理自然图像的DNN模型.
- 分析了表示中的视觉和语义属性的对齐和分歧.
主要成果:
- DNN 显示了视觉和语义维度的低维嵌入.
- 与语义特征相比,DNN更强调视觉特征,与人类表示不同.
- 直接比较显示了人类和DNN之间图像处理的实质差异,尽管DNN维度的明显可解释性.
结论:
- 拟议的框架允许直接比较人类和人工智能表示.
- 在人类和DNN之间的图像表示策略中发现了显著的差异.
- 调查结果强调了代表性调整的挑战,并提出了改善人工智能开发中的可比性方法.
相关概念视频
Directional Terms
12.9K
Directional terms are essential for describing the relative locations of different body structures. For instance, an anatomist might describe one band of tissue as "inferior to" another, or a physician might describe a tumor as "superficial to" a deeper body structure. These terms often use comparative terms in pairs to trace out the relative locations of one body part to another or descriptions of body tissues like the deeper ones from superficially present with reference to...
12.9K
Neural Circuits
1.6K
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...
1.6K
Depth Perception and Spatial Vision
972
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
972


