Information Field Theory and Artificial Intelligence

Information field theory (IFT), the information theory for fields, is a mathematical framework for signal reconstruction and non-parametric inverse problems. Artificial intelligence (AI) and machine learning (ML) aim at generating intelligent systems, including such for perception, cognition, and learning. This overlaps with IFT, which is designed to address perception, reasoning, and inference tasks. Here, the relation between concepts and tools in IFT and those in AI and ML research are discussed. In the context of IFT, fields denote physical quantities that change continuously as a function of space (and time) and information theory refers to Bayesian probabilistic logic equipped with the associated entropic information measures. Reconstructing a signal with IFT is a computational problem similar to training a generative neural network (GNN) in ML. In this paper, the process of inference in IFT is reformulated in terms of GNN training. In contrast to classical neural networks, IFT based GNNs can operate without pre-training thanks to incorporating expert knowledge into their architecture. Furthermore, the cross-fertilization of variational inference methods used in IFT and ML are discussed. These discussions suggest that IFT is well suited to address many problems in AI and ML research and application.     

Splitting an Arbitrary Three-Qubit State via a Five-Qubit Cluster State and a Bell State

Quantum information splitting (QIS) provides an idea for transmitting the quantum state through a classical channel and a preshared quantum entanglement resource. This paper presents a new scheme for QIS based on a five-qubit cluster state and a Bell state. In this scheme, the sender transmits the unknown three-qubit secret state to two agents by the quantum channel with the Bell basis measurement three times and broadcasts the measurement results to the agents through the classical channel. The agent who restores the secret state can successfully recover the initial information to be transmitted through the appropriate unitary operation with the help of the other party. Firstly, our scheme’s process can be accurately realized by performing the applicable Bell basis measurement, single-qubit measurement, and local unitary operation instead of a multiparticle joint measurement. The splitting process of quantum information is realized through a convenient operation. Secondly, compared with some previous schemes, the efficiency of the total scheme has been improved in principle, and the qubit consumption is reduced. Finally, the security of the quantum information splitting scheme is analyzed from the perspectives of external attacks and participant attacks. It is proved that our scheme can effectively resist internal participant attacks and external eavesdropper attacks.     

A Novel Approach to the Partial Information Decomposition

We consider the “partial information decomposition” (PID) problem, which aims to decompose the information that a set of source random variables provide about a target random variable into separate redundant, synergistic, union, and unique components. In the first part of this paper, we propose a general framework for constructing a multivariate PID. Our framework is defined in terms of a formal analogy with intersection and union from set theory, along with an ordering relation which specifies when one information source is more informative than another. Our definitions are algebraically and axiomatically motivated, and can be generalized to domains beyond Shannon information theory (such as algorithmic information theory and quantum information theory). In the second part of this paper, we use our general framework to define a PID in terms of the well-known Blackwell order, which has a fundamental operational interpretation. We demonstrate our approach on numerous examples and show that it overcomes many drawbacks associated with previous proposals.     

An Exploratory Study on the Complexity and Machine Learning Predictability of Stock Market Data

This paper shows if and how the predictability and complexity of stock market data changed over the last half-century and what influence the M1 money supply has. We use three different machine learning algorithms, i.e., a stochastic gradient descent linear regression, a lasso regression, and an XGBoost tree regression, to test the predictability of two stock market indices, the Dow Jones Industrial Average and the NASDAQ (National Association of Securities Dealers Automated Quotations) Composite. In addition, all data under study are discussed in the context of a variety of measures of signal complexity. The results of this complexity analysis are then linked with the machine learning results to discover trends and correlations between predictability and complexity. Our results show a decrease in predictability and an increase in complexity for more recent years. We find a correlation between approximate entropy, sample entropy, and the predictability of the employed machine learning algorithms on the data under study. This link between the predictability of machine learning algorithms and the mentioned entropy measures has not been shown before. It should be considered when analyzing and predicting complex time series data, e.g., stock market data, to e.g., identify regions of increased predictability.     

GDP vs. LDP: A Survey from the Perspective of Information-Theoretic Channel

The existing work has conducted in-depth research and analysis on global differential privacy (GDP) and local differential privacy (LDP) based on information theory. However, the data privacy preserving community does not systematically review and analyze GDP and LDP based on the information-theoretic channel model. To this end, we systematically reviewed GDP and LDP from the perspective of the information-theoretic channel in this survey. First, we presented the privacy threat model under information-theoretic channel. Second, we described and compared the information-theoretic channel models of GDP and LDP. Third, we summarized and analyzed definitions, privacy-utility metrics, properties, and mechanisms of GDP and LDP under their channel models. Finally, we discussed the open problems of GDP and LDP based on different types of information-theoretic channel models according to the above systematic review. Our main contribution provides a systematic survey of channel models, definitions, privacy-utility metrics, properties, and mechanisms for GDP and LDP from the perspective of information-theoretic channel and surveys the differential privacy synthetic data generation application using generative adversarial network and federated learning, respectively. Our work is helpful for systematically understanding the privacy threat model, definitions, privacy-utility metrics, properties, and mechanisms of GDP and LDP from the perspective of information-theoretic channel and promotes in-depth research and analysis of GDP and LDP based on different types of information-theoretic channel models.     

Retinex彩色图像增强理论的物理思考及其截断区间对图像质量的影响

指出了Retinex彩色图像增强理论的物理意义,在对数空间中,将原图像减去高斯函数与原图像的卷积,其物理本质是除去了原图像中的平滑的部分,突出了原图像中的快速变化的部分,而且高斯函数越尖锐,越是突出图像中的细节,高斯函数越平坦,图像色调保持得越好,多尺度Retinex综合了不同高斯函数与原图像进行卷积的优点。研究了多尺度Retinex标准差截断法,结果是,以多尺度Retinex处理后的图像强度在其平均值附近1倍标准差截断后再拉伸得到的图像,普遍好于以2倍、3倍标准差截断后再拉伸得到的图像。     

基于SuperMap的民政地理信息系统的设计与实现

以城市电子地图为基础数据,利用Visual Basic 6.0开发语言和SQL Server 2000关系数据库设计并实现基于SuperMap的民政地理信息系统.该系统具有地名管理、行政区划界限管理、门牌管理、城市地名、web信息发布、系统维护等功能,能够实现对城市地名及民政相关信息(道路、地形、水系等)的图形化存储与检索,以及信息的发布与浏览.     

基于启发式信息熵的粗集数值属性离散化算法

在一致性假设前提下,以数据集的统计性质作为启发式知识,从候选离散点集中选择离散点,根据数据集的期望值和方差来确定搜索最优离散点的区域,提出一种新的基于信息熵粗集数值属性离散化算法,并采用UCI国际标准数据集来验证新算法.新算法与已报道的算法所得到的离散断点集完全一致,决策表的离散化结果也相同,但时间代价不同,新算法比其计算效率提高40%～50%.     

利用蓝牙技术实现e-space资讯终端和e-casting广播系统

借鉴Internet、GSM、CDMA等信息网络服务的相关经验,按照self-help模型实现e-space资讯终端,按照push模型实现e-casting广播系统.e-space资讯终端是集计算机、无线通讯、以太网技术为一体的手机自助站系统,主要依托蓝牙、红外两种无线手段,实现手机图片、铃声、音乐、视频等下载,并具备手机数据上传功能,可将手机内的照片上传到自主站上进行编辑和输出打印.e-casting广播系统是一种信息推送工具,主要通过多个蓝牙接口,向广播站周围的蓝牙设备推送各类信息,可用于广告市场推广和公用信息广播.