在卷积神经网络中出现类似大脑的镜像对称视角调
Amirhossein Farzmahdi1,2, Wilbert Zarco1, Winrich A Freiwald1,3
1Laboratory of Neural Systems, The Rockefeller University, New York, United States.
eLife
|April 25, 2024
概括
在灵长类动物和深度学习模型中观察到的神经网络中的镜像对称视角调整,来自于学习识别双边对称的对象,而不仅仅是面孔.
科学领域:
- 计算神经科学是一种计算神经科学.
- 人工智能的人工智能是人工智能.
- 计算机视觉 计算机视觉 计算机视觉
背景情况:
- 灵长类动物对3D几何变化表现出对象识别不变性,但潜在的计算机制仍然不清楚.
- 镜子对称视角调整,神经元对反射的视角做出类似的反应,在子面部补丁AL和深 convolutional 网络中观察到.
- 这种镜像对称调整的发育起源,特别是对于面部,尚未完全理解.
研究的目的:
- 为神经网络中镜像对称视角调整提出并研究一种学习驱动的解释.
- 为了确定这种调是否出现在深层卷积网络中,即使没有明确的面部训练数据.
- 探索不同物体类别的镜像对称视角调整的概括性.
主要方法:
- 卷积深度神经网络被训练在物体识别任务使用多个视图呈现的3D对象.
- 用各种物体类别的刺激来测试镜对称视角调整,包括具有双边对称性的物体.
- 该研究分析了中间表示和空间聚合在下游单位中的作用.
主要成果:
- 镜面对称视角调整出现在训练对象识别的卷积神经网络的完全连接层中,无论面孔是否在训练集中.
- 这种调整不仅限于面孔,而且发生在具有双边对称性的多个对象类别中.
- 学习区分双边对称的对象诱导反射等价的中间表示,当空间聚合时,导致了类似AL的镜像对称调整.
结论:
- 神经网络中的镜面对称视角调整可以通过学习处理双边对称对象来解释.
- 这种现象不仅仅是面部,而且可以从暴露于更广泛的对称物体中出现.
- 这些发现为人造大脑和灵长类大脑中的镜像对称视角调整提供了一个计算理论,表明它可以超越训练的类别来概括.
相关概念视频
01:20Parallel Processing
150
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...
150
01:26Visual System
579
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
579