Abstract: It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic netw...Abstract: It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic network knowledge representation processing. A new extended Petri net is defined based on qualitative mapping, which strengths the expressive ability of the feature of thinking and the mode of action of brain. A model of semantic network knowledge representation based on new Petri net is given. Semantic network knowledge has a more efficient representation and reasoning mechanism. This model not only can reflect the characteristics of associative memory in semantic network knowledge representation, but also can use Petri net to express the criterion changes and its change law of recognition judgment, especially the cognitive operation of thinking based on extraction and integration of sensory characteristics to well express the thinking transition course from quantitative change to qualitative change of human cognition.展开更多
The aim of this work is mathematical education through the knowledge system and mathematical modeling. A net model of formation of mathematical knowledge as a deductive theory is suggested here. Within this model the ...The aim of this work is mathematical education through the knowledge system and mathematical modeling. A net model of formation of mathematical knowledge as a deductive theory is suggested here. Within this model the formation of deductive theory is represented as the development of a certain informational space, the elements of which are structured in the form of the orientated semantic net. This net is properly metrized and characterized by a certain system of coverings. It allows injecting net optimization parameters, regulating qualitative aspects of knowledge system under consideration. To regulate the creative processes of the formation and realization of mathematical know- edge, stochastic model of formation deductive theory is suggested here in the form of branching Markovian process, which is realized in the corresponding informational space as a semantic net. According to this stochastic model we can get correct foundation of criterion of optimization creative processes that leads to “great main points” strategy (GMP-strategy) in the process of realization of the effective control in the research work in the sphere of mathematics and its applications.展开更多
Introduce a method of generation of new units within a cluster and aalgorithm of generating new clusters. The model automatically builds up its dynamically growinginternal representation structure during the learning ...Introduce a method of generation of new units within a cluster and aalgorithm of generating new clusters. The model automatically builds up its dynamically growinginternal representation structure during the learning process. Comparing model with other typicalclassification algorithm such as the Kohonen's self-organizing map, the model realizes a multilevelclassification of the input pattern with an optional accuracy and gives a strong support possibilityfor the parallel computational main processor. The idea is suitable for the high-level storage ofcomplex datas structures for object recognition.展开更多
With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery ...With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery of knowledge based on their historical exercise sequences. Nowadays, many related works have emerged in this field, such as Bayesian knowledge tracing and deep knowledge tracing methods. Despite the progress that has been made in KT, existing techniques still have the following limitations: 1) Previous studies address KT by only exploring the observational sparsity data distribution, and the counterfactual data distribution has been largely ignored. 2) Current works designed for KT only consider either the entity relationships between questions and concepts, or the relations between two concepts, and none of them investigates the relations among students, questions, and concepts, simultaneously, leading to inaccurate student modeling. To address the above limitations,we propose a graph counterfactual augmentation method for knowledge tracing. Concretely, to consider the multiple relationships among different entities, we first uniform students, questions, and concepts in graphs, and then leverage a heterogeneous graph convolutional network to conduct representation learning.To model the counterfactual world, we conduct counterfactual transformations on students’ learning graphs by changing the corresponding treatments and then exploit the counterfactual outcomes in a contrastive learning framework. We conduct extensive experiments on three real-world datasets, and the experimental results demonstrate the superiority of our proposed Graph CA method compared with several state-of-the-art baselines.展开更多
Remarkable progress in research has shown the efficiency of Knowledge Graphs(KGs)in extracting valuable external knowledge in various domains.A Knowledge Graph(KG)can illustrate high-order relations that connect two o...Remarkable progress in research has shown the efficiency of Knowledge Graphs(KGs)in extracting valuable external knowledge in various domains.A Knowledge Graph(KG)can illustrate high-order relations that connect two objects with one or multiple related attributes.The emerging Graph Neural Networks(GNN)can extract both object characteristics and relations from KGs.This paper presents how Machine Learning(ML)meets the Semantic Web and how KGs are related to Neural Networks and Deep Learning.The paper also highlights important aspects of this area of research,discussing open issues such as the bias hidden in KGs at different levels of graph representation。展开更多
知识蒸馏的核心思想是利用1个作为教师网络的大型模型来指导1个作为学生网络的小型模型,提升学生网络在图像分类任务上的性能.现有知识蒸馏方法通常从单一的输入样本中提取类别概率或特征信息作为知识,并没有对样本间关系进行建模,造成...知识蒸馏的核心思想是利用1个作为教师网络的大型模型来指导1个作为学生网络的小型模型,提升学生网络在图像分类任务上的性能.现有知识蒸馏方法通常从单一的输入样本中提取类别概率或特征信息作为知识,并没有对样本间关系进行建模,造成网络的表征学习能力下降.为解决此问题,本文引入图卷积神经网络,将输入样本集视为图结点构建关系图,图中的每个样本都可以聚合其他样本信息,提升样本的表征能力.本文从图结点和图关系2个角度构建图表征知识蒸馏误差,利用元学习引导学生网络自适应学习教师网络更佳的图表征,提升学生网络的图建模能力.相比于基线方法,本文提出的图表征知识蒸馏方法在加拿大高等研究院(Canadian Institute For Advanced Research,CIFAR)发布的100种分类数据集上提升了3.70%的分类准确率,表明本文方法引导学生网络学习到了更具有判别性的特征空间,提升了图像分类能力.展开更多
当前,针对知识网络的链路预测主要是基于网络拓扑结构的相似性,很少考虑作者的研究领域,导致信息利用不充分等问题,因此本文提出了双层知识网络的链路预测框架hypernet2vec。双层知识网络,即作者合著关系网络和学术领域关系网络,利用网...当前,针对知识网络的链路预测主要是基于网络拓扑结构的相似性,很少考虑作者的研究领域,导致信息利用不充分等问题,因此本文提出了双层知识网络的链路预测框架hypernet2vec。双层知识网络,即作者合著关系网络和学术领域关系网络,利用网络表示学习,分别将两层网络中的节点映射到低维的向量空间,再输入到专门设计的卷积神经网络中计算并进行链路预测。与经典的链路预测指标如RA指标、LP指标和LRW指标等相比,hypernet2vec模型预测的AUC(area under curve)值取得了显著的提升,平均提升幅度达11.17%。文章还从情报产生层面和复杂系统层面,对模型发生作用的深层机理进行了探讨。展开更多
文摘Abstract: It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic network knowledge representation processing. A new extended Petri net is defined based on qualitative mapping, which strengths the expressive ability of the feature of thinking and the mode of action of brain. A model of semantic network knowledge representation based on new Petri net is given. Semantic network knowledge has a more efficient representation and reasoning mechanism. This model not only can reflect the characteristics of associative memory in semantic network knowledge representation, but also can use Petri net to express the criterion changes and its change law of recognition judgment, especially the cognitive operation of thinking based on extraction and integration of sensory characteristics to well express the thinking transition course from quantitative change to qualitative change of human cognition.
文摘The aim of this work is mathematical education through the knowledge system and mathematical modeling. A net model of formation of mathematical knowledge as a deductive theory is suggested here. Within this model the formation of deductive theory is represented as the development of a certain informational space, the elements of which are structured in the form of the orientated semantic net. This net is properly metrized and characterized by a certain system of coverings. It allows injecting net optimization parameters, regulating qualitative aspects of knowledge system under consideration. To regulate the creative processes of the formation and realization of mathematical know- edge, stochastic model of formation deductive theory is suggested here in the form of branching Markovian process, which is realized in the corresponding informational space as a semantic net. According to this stochastic model we can get correct foundation of criterion of optimization creative processes that leads to “great main points” strategy (GMP-strategy) in the process of realization of the effective control in the research work in the sphere of mathematics and its applications.
基金Supported by the National"Fifteenth Year Plan"Key Project(2001BA307B01 02 01)
文摘Introduce a method of generation of new units within a cluster and aalgorithm of generating new clusters. The model automatically builds up its dynamically growinginternal representation structure during the learning process. Comparing model with other typicalclassification algorithm such as the Kohonen's self-organizing map, the model realizes a multilevelclassification of the input pattern with an optional accuracy and gives a strong support possibilityfor the parallel computational main processor. The idea is suitable for the high-level storage ofcomplex datas structures for object recognition.
基金supported by the Natural Science Foundation of China (62372277)the Natural Science Foundation of Shandong Province (ZR2022MF257, ZR2022MF295)Humanities and Social Sciences Fund of the Ministry of Education (21YJC630157)。
文摘With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery of knowledge based on their historical exercise sequences. Nowadays, many related works have emerged in this field, such as Bayesian knowledge tracing and deep knowledge tracing methods. Despite the progress that has been made in KT, existing techniques still have the following limitations: 1) Previous studies address KT by only exploring the observational sparsity data distribution, and the counterfactual data distribution has been largely ignored. 2) Current works designed for KT only consider either the entity relationships between questions and concepts, or the relations between two concepts, and none of them investigates the relations among students, questions, and concepts, simultaneously, leading to inaccurate student modeling. To address the above limitations,we propose a graph counterfactual augmentation method for knowledge tracing. Concretely, to consider the multiple relationships among different entities, we first uniform students, questions, and concepts in graphs, and then leverage a heterogeneous graph convolutional network to conduct representation learning.To model the counterfactual world, we conduct counterfactual transformations on students’ learning graphs by changing the corresponding treatments and then exploit the counterfactual outcomes in a contrastive learning framework. We conduct extensive experiments on three real-world datasets, and the experimental results demonstrate the superiority of our proposed Graph CA method compared with several state-of-the-art baselines.
文摘Remarkable progress in research has shown the efficiency of Knowledge Graphs(KGs)in extracting valuable external knowledge in various domains.A Knowledge Graph(KG)can illustrate high-order relations that connect two objects with one or multiple related attributes.The emerging Graph Neural Networks(GNN)can extract both object characteristics and relations from KGs.This paper presents how Machine Learning(ML)meets the Semantic Web and how KGs are related to Neural Networks and Deep Learning.The paper also highlights important aspects of this area of research,discussing open issues such as the bias hidden in KGs at different levels of graph representation。
文摘知识蒸馏的核心思想是利用1个作为教师网络的大型模型来指导1个作为学生网络的小型模型,提升学生网络在图像分类任务上的性能.现有知识蒸馏方法通常从单一的输入样本中提取类别概率或特征信息作为知识,并没有对样本间关系进行建模,造成网络的表征学习能力下降.为解决此问题,本文引入图卷积神经网络,将输入样本集视为图结点构建关系图,图中的每个样本都可以聚合其他样本信息,提升样本的表征能力.本文从图结点和图关系2个角度构建图表征知识蒸馏误差,利用元学习引导学生网络自适应学习教师网络更佳的图表征,提升学生网络的图建模能力.相比于基线方法,本文提出的图表征知识蒸馏方法在加拿大高等研究院(Canadian Institute For Advanced Research,CIFAR)发布的100种分类数据集上提升了3.70%的分类准确率,表明本文方法引导学生网络学习到了更具有判别性的特征空间,提升了图像分类能力.
文摘当前,针对知识网络的链路预测主要是基于网络拓扑结构的相似性,很少考虑作者的研究领域,导致信息利用不充分等问题,因此本文提出了双层知识网络的链路预测框架hypernet2vec。双层知识网络,即作者合著关系网络和学术领域关系网络,利用网络表示学习,分别将两层网络中的节点映射到低维的向量空间,再输入到专门设计的卷积神经网络中计算并进行链路预测。与经典的链路预测指标如RA指标、LP指标和LRW指标等相比,hypernet2vec模型预测的AUC(area under curve)值取得了显著的提升,平均提升幅度达11.17%。文章还从情报产生层面和复杂系统层面,对模型发生作用的深层机理进行了探讨。