An axiom system for sequence-based specification

This paper establishes an axiomatic foundation and a representation theorem for the rigorous, constructive process, called sequence-based specification, of deriving precise specifications from ordinary (informal) statements of functional requirements. The representation theorem targets a special class of Mealy state machines, and algorithms are presented for converting from the set of sequences that define the specification to the equivalent Mealy machine, and vice versa. Since its inception, sequence-based specification has been effectively used in a variety of real applications, with gains reported in quality and productivity. This paper establishes the mathematical foundation independently of the process itself.     

Compositional pattern producing networks: A novel abstraction of development

Natural DNA can encode complexity on an enormous scale. Researchers are attempting to achieve the same representational efficiency in computers by implementing developmental encodings, i.e. encodings that map the genotype to the phenotype through a process of growth from a small starting point to a mature form. A major challenge in in this effort is to find the right level of abstraction of biological development to capture its essential properties without introducing unnecessary inefficiencies. In this paper, a novel abstraction of natural development, called Compositional Pattern Producing Networks (CPPNs), is proposed. Unlike currently accepted abstractions such as iterative rewrite systems and cellular growth simulations, CPPNs map to the phenotype without local interaction, that is, each individual component of the phenotype is determined independently of every other component. Results produced with CPPNs through interactive evolution of two-dimensional images show that such an encoding can nevertheless produce structural motifs often attributed to more conventional developmental abstractions, suggesting that local interaction may not be essential to the desirable properties of natural encoding in the way that is usually assumed.

Invariants for the computation of intransitive and transitive Galois groups

One hard step in the computation of Galois groups by Stauduhar’s method is the construction of relative invariants. In this note, a representation-theoretic approach is given for the construction in the case of an intransitive group.In the second part of the article, it is shown that the construction can be used for groups that have a suitable intransitive subgroup. The construction solves an open question of Fieker and Klüners.     

Semantic Web: A road to the knowledge infrastructure on the internet

In this article, I describe the basic technologies for Semantic Web and relationship between Semantic Web and Knowledge Representation in Artificial Intelligence. Semantic Web is planned as an extension of the current web in order to help cooperation between computers and humans, i.e., computers and humans are expected to understand each other in the knowledge level. I first describe the vision of the Semantic Web, then introduce the current Semantic Web technologies, i.e., RDF, RDFS, and OWL. I describe relationship between the trend of Semantic Web and Knowledge Representation, and clarify challenges and difficulties of Semantic Web from the point of view of Knowledge Representation. Hideaki Takeda: He is a professor at National Institute of Informatics (NII) and a professor in Department of Informatics at the Graduate University of Advanced Studies (Sokendai). He received his Ph.D. from the University of Tokyo in 1991. His research interest in computer science includes ontology engineering, community informatics and knowledge sharing systems.     

基于本体的数学知识获取与知识继承机制研究

基于本体、框架和逻辑给出了数学知识表示语言，采用了面向概念的数学知识获取方法，利用半自动的方式对数学知识进行了获取。提出了知识树的概念用于所获得的知识的管理，设计并实现了数学知识获取和管理平台。研究了数学概念知识体系结构以及概念之间的知识继承机制，并对知识继承的一致性进行了分析。在数学知识的应用方面，对基于Web的数学知识问答系统、数学智能教学系统、数学知识的多语言版本自动生成等进行了初步的探讨。     

Learning knowledge representation with meta knowledge distillation for single image super-resolution

Although the deep CNN-based super-resolution methods have achieved outstanding performance, their memory cost and computational complexity severely limit their practical employment. Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The representation of knowledge is vital for knowledge transferring and student learning, which is generally defined in hand-crafted manners or uses the intermediate features directly. In this paper, we propose a model-agnostic meta knowledge distillation method under the teacher–student architecture for the single image super-resolution task. It provides a more flexible and accurate way to help teachers transmit knowledge in accordance with the abilities of students via knowledge representation networks (KRNets) with learnable parameters. Specifically, the texture-aware dynamic kernels are generated from local information to decompose the distillation problem into texture-wise supervision for further promoting the recovery quality of high-frequency details. In addition, the KRNets are optimized in a meta-learning manner to ensure the knowledge transferring and the student learning are beneficial to improving the reconstructed quality of the student. Experiments conducted on various single image super-resolution datasets demonstrate that our proposed method outperforms existing defined knowledge representation-related distillation methods and can help super-resolution algorithms achieve better reconstruction quality without introducing any extra inference complexity.     

Variational Feature Representation-based Classification for face recognition with single sample per person

The single sample per person (SSPP) problem is of great importance for real-world face recognition systems. In SSPP scenario, there is always a large gap between a normal sample enrolled in the gallery set and the non-ideal probe sample. It is a crucial step for face recognition with SSPP to bridge the gap between the ideal and non-ideal samples. For this purpose, we propose a Variational Feature Representation-based Classification (VFRC) method, which employs the linear regression model to fit the variational information of a non-ideal probe sample with respect to an ideal gallery sample. Thus, a corresponding normal feature, which reserve the identity information of the probe sample, is obtained. A combination of the normal feature and the probe sample is used, which makes VFRC method more robust and effective for SSPP scenario. The experimental results show that VFRC method possesses higher recognition rate than other related face recognition methods.     

一种基于图注意力网络的异质信息网络表示学习框架

常用的异质信息网络有知识图谱和具有简单模式层的异质信息网络,它们的表示学习通常遵循不同的方法。该文总结了知识图谱和具有简单模式层的异质信息网络之间的异同,提出了一个通用的异质信息网络表示学习框架。该文提出的框架可以分为3个部分：基础向量模型,基于图注意力网络的传播模型以及任务模型。基础向量模型用于学习基础的网络向量;传播模型通过堆叠注意力层学习网络的高阶邻居特征;可更换的任务模型适用于不同的应用场景。与基准模型相比,该文所提框架在知识图谱的链接预测任务和异质信息网络的节点分类任务中都取得了相对不错的效果。     

基于弧度距离的时间序列相似度量

时间序列的近似表示和相似度量是时间序列数据挖掘的重要任务之一,是进行相似匹配的关键。该文针对现有的各种基于分段线性表示(Piecewise Linear Representation,PLR)相似度量方法存在的序列长度依赖和多分辨率条件下的潜在识别误差等缺点,提出了一种序列分段线性弧度表示和基于弧度距离的相似度量方法,实现了序列的快速在线分割和相似度计算。该方法简洁直观,利用分段弧度对分段趋势进行细粒度划分来保留序列主要形态特征,有效地提高了度量结果的准确性和多分辨率条件下的稳定性。该方法具有序列分割算法独立性特点,可用于时间序列的相似查询、模式匹配、分类和聚类。