A Study of the Robustness of KNN Classifiers Trained Using Soft Labels

Abstract

Supervised learning models most commonly use crisp labels for classifier training. Crisp labels fail to capture the data characteristics when overlapping classes exist. In this work we attempt to compare between learning using soft and hard labels to train K-nearest neighbor classifiers. We propose a new technique to generate soft labels based on fuzzy-clustering of the data and fuzzy relabelling of cluster prototypes. Experiments were conducted on five data sets to compare between classifiers that learn using different types of soft labels and classifiers that learn with crisp labels. Results reveal that learning with soft labels is more robust against label errors opposed to learning with crisp labels. The proposed technique to find soft labels from the data, was also found to lead to a more robust training in most data sets investigated.

Multi-label Learning with Label Enhancement

“…Though there is no explicit definition of LE defined in existing literatures, some methods with similar function to LE have been proposed in the past years. In [20] and [21], the membership degrees to the labels are constructed via fuzzy clustering [22] and kernel method. However, these two methods have not been applied to multi-label learning.…”

Label distribution learning and label enhancement

“…. , y c } 表示标记空 间, 则面向标记分布学习的标记增强定义如下: 基于模糊聚类的标记增强 [12] 通过模糊 C -均值聚类 (fuzzy C-means algorithm, FCM) [16] 和模 糊运算, 将训练集中每个示例的逻辑标记转化为相应的标记分布, 从而得到标记分布训练集…”

Adjustment of Wavelet Filters for Image Compression Using Artificial Intelligence

“…Se clasifica a la clase del patrón k más cercano, donde k es un entero positivo generalmente impar. Desde los artículos pioneros de este método hasta modificaciones al método original como los presentados en [24], [25], [26], [27], [28] en los cuales se presentan variación del método original o la combinación de clasificadores. Los cuales han demostrado en las diferentes aplicaciones que se ha utilizado este método, que es uno de más eficientes que existen para el reconocimiento y clasificación de patrones.…”