incremental learning

Based on the out-of-sample framework and the graph embedding framework, the thesis presents a more general common framework for manifold learning. The new framework embodies graph construction, tensor learning, incremental learning and supervised learning.

提出新的流形学习统一框架在样本泛化与图嵌理论的基础上，提出了更一般的流形学习统一框架，这一框架包含了图的建立、张量学习、增量学习和有监督学习。

A weighted class incremental learning algorithm is presented, which improves the CIL algorithm. The algorithm adds the weighs of class to training samples.

提出了一种加权类增量学习算法，该算法是对CIL算法的改进，通过加入类权值，解决了因两类训练样本不平衡而造成的小类别分类精度较低的问题。

An incremental learning algorithm using multiple support vector machines ( SVMs) is proposed.

给出了使用多支持向量机进行增量学习的算法。

Besides, based on hyper sphere SVMs, a new class incremental learning algorithm is presented.

同时，提出了一种新的类增量学习算法，该算法利用超球支持向量机进行分类。

Model experiments show that, the financial distress prediction model based on the incremental learning system is stable and adaptable. Incremental prediction model outperforms other models, which is an effective financial distress prediction method.

财务数据实验表明，基于增量学习系统的财务危机预警模型兼具稳定性和适应性，模型预测性能优于滑动时间窗口模型，是一种有效的财务危机预警建模方法。

When tagging a large number of categories with high price of the sample, combined with the incremental learning theory is an effective way to solve the problem.

当获得大量带有类别标注的样本代价较高时，与增量学习理论结合是解决问题的有效途径。

The incremental learning algorithm in hybrid learning model HLM

混合型学习模型HLM中的增量学习算法

Multi-class Incremental Learning Based on Support Vector Machines

基于支持向量机的多分类增量学习算法

As an incremental learning system, Case-based reasoning ( CBR) makes the knowledge and rule obtainment bottleneck easy by learning from case, thus it has increasingly become a hotspot in the area of artificial intelligent.

基于事例的推理（CBR）作为一种增量式的学习方法，规避了传统人工智能在知识获取上的瓶颈问题，逐渐引起人工智能领域研究者的关注。