RI: Small: A Hierarchical Approach to Unsupervised Feature Discovery

RI：小型：无监督特征发现的分层方法

• 批准号: 1219252
• 负责人: Garrison Cottrell
• 金额: $ 40万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-09-01 至 2016-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1219252&HistoricalAwards=false
• 关键词: RI; Small; Hierarchical; Approach; Unsupervised

Contrary to some depictions in popular media, humans are still far better than any computer program at understanding the visual world around them. If we understood how the visual system does this, perhaps better artificial vision systems could be built. The goal of this project is to understand how the brain represents the visual world and why. Following a mantra famously credited to Richard Feynman -- What I cannot create, I do not understand -- this project's approach is to create a computer system that learns from natural input (images, videos), assuming that the visual system operates with the goal of efficiently representing the world. These representations will then be compared to measurements of visual neurons. The long term goal is to understand the functional roles of the early visual processing layers in the human visual pathway.The model is based on the efficient coding hypothesis, in which the early visual pathway serves to capture the statistical structure of its visual inputs by efficiently coding visual information in its outputs. Most computational models following this hypothesis have focused on modeling only one or two visual layers. In this project, Cottrell's group proposes a hierarchical information processing model, which concurs with the efficient coding hypothesis, yet provides the most complete description so far of the early visual processing layers. In this model, the visual inputs are first compressed to reduce noise using Sparse Principal Components Analysis (SPCA), then the data dimensions are expanded to capture the statistical structure of the visual inputs using overcomplete Sparse Coding. A nonlinear activation function then formats the outputs of this layer for the next layer up, and the whole process is repeated. Preliminary work shows that the resulting hierarchical model can learn visual features exhibiting the receptive field properties of neurons in the early visual pathway, including retinal ganglion cells, LGN, V1 simple and complex cells, and V2 cells.

与流行媒体中的某些描述相反，人类在了解周围的视觉世界方面仍然比任何计算机程序要好得多。如果我们了解视觉系统是如何执行此操作的，那么也许可以构建更好的人造视觉系统。该项目的目的是了解大脑如何代表视觉世界以及原因。在著名地归功于理查德·费曼（Richard Feynman）的咒语之后 - 我无法创建的东西，我不明白 - 该项目的方法是创建一个从自然输入（图像，视频）中学习的计算机系统，假设视觉系统的运作旨在有效地代表世界。然后将这些表示与视觉神经元的测量值进行比较。长期目标是了解人类视觉途径中早期视觉处理层的功能作用。该模型基于有效的编码假设，在该假说中，早期的视觉途径通过在其输出中有效地编码视觉信息来捕获其视觉输入的统计结构。遵循此假设的大多数计算模型都集中在建模仅一两个视觉层。在这个项目中，Cottrell的小组提出了一个分层信息处理模型，该模型与有效的编码假设一致，但在早期的视觉处理层中提供了最完整的描述。在此模型中，首先将视觉输入压缩以使用稀疏主组件分析（SPCA）降低噪声，然后扩展数据尺寸，以使用过度complete的稀疏编码来捕获视觉输入的统计结构。然后，非线性激活函数将此层的输出格式化为下一个层，然后重复整个过程。初步工作表明，所得的层次模型可以学习在早期视觉途径中表现出神经元的接受场特性的视觉特征，包括视网膜神经节细胞，LGN，V1简单和复杂的细胞和V2细胞。