A Model for Learning Topographically Organized Parts-Based Representations of Objects in Visual Cortex: Topographic Nonnegative Matrix Factorization
A Model for Learning Topographically Organized Parts-Based Representations of Objects in Visual Cortex: Topographic Nonnegative Matrix Factorization
复制标题
DOI：
10.1162/neco.2009.03-08-722
复制
发表时间：
2009-09-01
影响因子：
2.9
通讯作者：
Fujita, Ichiro
中科院分区：
文献类型：
--
作者：
Hosoda, Kenji;Watanabe, Masataka;Fujita, Ichiro
下颞叶皮层（IT）是灵长类动物视觉皮层中对物体识别至关重要的区域，其物体表征表现出两个显着的特性：（1）物体由柱状神经元簇的组合活动来表征，每个簇代表物体的组成特征或部分；（2）沿着各个柱状簇的切线方向连续地表征密切相关的特征。在这里，我们提出了一种学习模型，该模型在统一的框架中反映了基于部件的表示和拓扑组织的这些属性。该模型基于非负矩阵分解 (NMF) 基分解方法。 NMF 单独提供了基于部分的表示，其中非负输入通过非负基函数的加法组合来近似。我们提出的地形 NMF (TNMF) 模型结合了地形图上排列的 NMF 基函数之间的邻域连接，并在不丢失 NMF 的基于部分的属性的情况下获得了地形属性。 TNMF 表示多个活动峰的输入来描述不同的信息，而传统的地形模型，例如自组织图 (SOM)，表示地形图中单个活动峰的输入。我们通过构建对象识别的分层模型来演示 TNMF 的基于部件和地形的属性，其中 TNMF 位于学习高级对象特征的顶层。对于图像的连续视图变化的数据集，TNMF 表现出比 NMF 更好的泛化性能，并且更稳健地保持其对象表示中视图变化的连续性。我们模型的输出与 IT 中记录的实际神经反应的比较表明，TNMF 比 SOM 更好地重建了神经元反应，这为模型的基于部分的学习提供了合理性。
Object representation in the inferior temporal cortex (IT), an area of visual cortex critical for object recognition in the primate, exhibits two prominent properties: (1) objects are represented by the combined activity of columnar clusters of neurons, with each cluster representing component features or parts of objects, and (2) closely related features are continuously represented along the tangential direction of individual columnar clusters. Here we propose a learning model that reflects these properties of parts-based representation and topographic organization in a unified framework. This model is based on a nonnegative matrix factorization (NMF) basis decomposition method. NMF alone provides a parts-based representation where nonnegative inputs are approximated by additive combinations of nonnegative basis functions. Our proposed model of topographic NMF (TNMF) incorporates neighborhood connections between NMF basis functions arranged on a topographic map and attains the topographic property without losing the parts-based property of the NMF. The TNMF represents an input by multiple activity peaks to describe diverse information, whereas conventional topographic models, such as the self-organizing map (SOM), represent an input by a single activity peak in a topographic map. We demonstrate the parts-based and topographic properties of the TNMF by constructing a hierarchical model for object recognition where the TNMF is at the top tier for learning high-level object features. The TNMF showed better generalization performance over NMF for a data set of continuous view change of an image and more robustly preserving the continuity of the view change in its object representation. Comparison of the outputs of our model with actual neural responses recorded in the IT indicates that the TNMF reconstructs the neuronal responses better than the SOM, giving plausibility to the parts-based learning of the model.