视觉皮层的高性能神经网络模型从高潜在维度中受益
Eric Elmoznino1, Michael F Bonner1
1Department of Cognitive Science, Johns Hopkins University, Baltimore, Maryland, United States of America.
PLoS computational biology
|January 10, 2024
概括
与普遍认为的相反,模拟视觉皮层的深度神经网络 (DNN) 从高维表示中受益. 这种几何性质提高了预测神经反应和学习新的视觉类别的概括性能.
科学领域:
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
- 计算机视觉 计算机视觉
背景情况:
- 深度神经网络 (DNN) 的几何描述为神经科学中使用的计算模型提供了洞察力.
- 一个普遍的假设表明,最优的DNN利用低维表示不变性和稳定性.
- 这意味着视觉皮层的高级模型应该表现出更低维的几何形状.
研究的目的:
- 为了研究视觉皮层的DNN模型的几何.
- 在这些模型中量化自然图像表示的潜在维度.
- 在预测神经反应方面,将表示几何与概括性能联系起来.
主要方法:
- 检查了视觉皮层的DNN模型.
- 自然图像表示的量化潜在维度.
- 评估了使用子电生理学和人类fMRI数据对持有刺激的概括性能.
主要成果:
- 发现了一个与普遍假设相反的趋势:更高维度图像子空间与更好的概括相关.
- 高维度在子和人类数据集中更准确地预测皮质反应.
- 更高的维度表示与学习新的刺激类别的性能提高有关.
结论:
- 高维几何学为视觉皮层的DNN模型提供了计算优势.
- 增加的维度增强了超越培训领域的概括能力.
- 挑战了低维压缩对于视觉皮层模型来说是普遍最佳的概念.
相关概念视频
Vision
53.4K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.4K
Visual System
585
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...
585
Parallel Processing
152
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...
152
Motor and Sensory Areas of the Cortex
3.9K
The cerebral cortex, the brain's outermost layer, is pivotal in processing complex cognitive tasks, emotions, and various sensory inputs and executing voluntary motor activities. This intricate structure is divided into three primary functional areas: the motor areas, sensory areas, and association areas.
Motor Areas
The motor areas located in the frontal lobe are central to controlling voluntary movements. This region is further subdivided into the primary motor cortex and the premotor cortex....
Motor Areas
The motor areas located in the frontal lobe are central to controlling voluntary movements. This region is further subdivided into the primary motor cortex and the premotor cortex....
3.9K
Somatosensory, Motor, and Association Cortex
514
The somatosensory cortex in the parietal lobes is crucial for interpreting sensory data such as touch, temperature, and proprioception. The somatosensory cortex, situated in the parietal lobes, plays a vital role in interpreting sensory information like touch, temperature, and proprioception—awareness of body position. This specialized brain region features an organized structure wherein neurons at the top primarily process sensations originating from the lower body. In contrast, those at...
514
Depth Perception and Spatial Vision
657
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.
657


