arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1012.4126cs.NEcs.CV
收藏

自组织随机编码器

Self-Organising Stochastic Encoders

Stephen Luttrell

摘要:

只有在使用固定大小的处理窗口时,诸如图像的兆维数据的处理才与图像大小成线性比例。如果能够自动调整处理窗口的大小并将其相互连接,这将非常有用。随机编码器是标准Linde-Buzo-Gray矢量量化器的扩展,称为随机矢量量化器(SVQ),包括其涌现属性中的所需行为,因为它自动将输入空间划分为统计独立的子空间,然后单独编码。各种最佳的SVQ已获得,无论是分析和数值。当SVQ用于编码存在于2-环面上的数据(例如,一对不相关的正弦曲线的叠加)时,可以获得演示输入空间如何被分成独立子空间的解析解。使用SVQ和链接的SVQ链也获得了许多数值解:(1)多个独立目标的图像(出现了用于单个目标的编码器),(2)多个相关目标的图像(出现了用于单个和多个目标的各种类型的编码器),(3)各种波形的叠加(出现用于单独波形的编码器-这是一种独立分量分析(ICA)),(4)母体和胎儿ECG(ICA的另一个例子),(5)纹理图像(方向图和优势条纹出现)。总体而言,SVQ表现出丰富多样的自组织行为,有效地发现了训练数据的内部结构。这应该对“智能”计算产生直接影响,因为它减少了在数据处理算法设计中对专家人工干预的需求。

英文摘要:

The processing of mega-dimensional data, such as images, scales linearly with image size only if fixed size processing windows are used. It would be very useful to be able to automate the process of sizing and interconnecting the processing windows. A stochastic encoder that is an extension of the standard Linde-Buzo-Gray vector quantiser, called a stochastic vector quantiser (SVQ), includes this required behaviour amongst its emergent properties, because it automatically splits the input space into statistically independent subspaces, which it then separately encodes. Various optimal SVQs have been obtained, both analytically and numerically. Analytic solutions which demonstrate how the input space is split into independent subspaces may be obtained when an SVQ is used to encode data that lives on a 2-torus (e.g. the superposition of a pair of uncorrelated sinusoids). Many numerical solutions have also been obtained, using both SVQs and chains of linked SVQs: (1) images of multiple independent targets (encoders for single targets emerge), (2) images of multiple correlated targets (various types of encoder for single and multiple targets emerge), (3) superpositions of various waveforms (encoders for the separate waveforms emerge - this is a type of independent component analysis (ICA)), (4) maternal and foetal ECGs (another example of ICA), (5) images of textures (orientation maps and dominance stripes emerge). Overall, SVQs exhibit a rich variety of self-organising behaviour, which effectively discovers the internal structure of the training data. This should have an immediate impact on "intelligent" computation, because it reduces the need for expert human intervention in the design of data processing algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑