支持规则推理的神经网络模型

本文研究了支持规则推理的神经网络模型，表明通常执行的推理与符号系统在方法上确实相似，只是它们对常识推理提供了更多的方法。CONSYDERR是一种支持常识推理的连接结构，其目的是给出常识推理的一种模型，并纠正传统规则系统中的脆弱性问题。本项工作表明，推理的连接模型不仅实现了符号推理，而且是一种更好的常识推理的计算模型。     

面向对象推理机的设计

本文利用面向对象编程技术建立了一个推理机模型，并提出一种提高推理效率的方法。利用此模型，进行高炉热状态水平预报，取得良好推理效果，并使系统推理效率大大提高。     

扩展时段时序逻辑的模型、一致性和推理

给出了扩展时段时序逻辑的时间Petri网（TPN）模型构造方法，在构造模型的同时对时序关系进行一致性检验，在模型的基础上提出了一种时序关系推理算法，这种推理算法基于TPN模型的性质及基本不等式规则，可由一组已知的扩展时段时序关系推出一些未知的扩展时段时序关系，这种推广理算法的优势在于利用了TNP模型的分析技术，减小了推理的时间复杂度比单纯利用不等式规则的推理更直观，也更简单，是一种有效的方法，最后，对扩展时段时序逻辑的TPN模型进行了扩充，增强了其模型和分析的能力。     

模糊Petri网及知识表示

在建造专家系统中虽然有很多种知识表示方法，但都有不尽人意的地方，本文试图用一种新的方法－Ｐｅｔｒｉ网模型来表示知识。本文给出了Ｆｕｚｚｚｙ Ｐｅｔｒｉ网和广义Ｆｕｚｚｙ Ｐｅｔｒｉ网两种模型，并给出了相应的推理算法，一旦专家知识用Ｐｅｔｒｉ网表示后，根据Ｐｅｔｒｉ网固有的特性，我们就能处理专家系统中并行推理、无回溯推理，反向推理等问题。     

扩展时段时序逻辑的推理机制

该文在扩展时段时序逻辑的基础上提出了一种推理机制，这种推理机制基于时间Petri网模型及基本不等式规则，可由一组已知的扩展时段时序关系推出一些未知的扩展时段时序关系，对不确定时间段内发生的事件及其相互关系具有较好的描述能力，这种推理机制的优势在于定性地对扩展时段之间的时序关系进行推理分析，利用时间Petri网模型，可以对复杂时序逻辑关系进行化简，比单纯利用不等式规则的推理更直观，也更简单，是一种行之有效的方法。     

基于规则推理的FPN误用入侵检测方法

针对网络入侵攻击活动的模糊性，提出了一种基于模糊推理的模糊Petri网（FPN）误用入侵检测方法。该方法定义了一个六元组FPN，并将模糊产生式规则精化为两种基本类型。在此基础上给出了FPN表示模糊规则的模型、推理过程和基于FPN的推理算法。最后通过入侵检测的实例对该方法的正确性和有效性进行了验证，结果表明该方法推理过程简单直观、容易实现，而且具有并行推理能力，可适用于大规模的FPN模型，是误用入侵检测技术的一种非常有效的解决方案。     

一个基于插值的模糊控制器的推理方法

文章提出了一种基于插值的模糊控制器,它既保持了合成推理的灵活性,同时又简化了合成推理的复杂性.在此基础上,给出了三种插值模型：线性插值模型,平方插值模型以及拉格朗日插值模型,最后给出了一个实例并对合成推理和三种插值模型进行了比较.     

异构平台下卷积神经网络推理模型自适应划分和调度方法

针对卷积神经网络（CNN）在异构平台执行推理时存在硬件资源利用率低、延迟高等问题，提出一种CNN推理模型自适应划分和调度方法。首先，通过遍历计算图提取CNN的关键算子完成模型的自适应划分，增强调度策略灵活性；然后，基于性能实测与关键路径-贪婪搜索算法，在CPU-GPU异构平台上根据子模型运行特征选取最优运行负载，提高子模型推理速度；最后利用张量虚拟机（TVM）中跨设备调度机制，配置子模型的依赖关系与运行负载，实现模型推理的自适应调度，降低设备间通信延迟。实验结果表明，与TVM算子优化方法在GPU和CPU上的推理速度相比，所提方法在模型推理准确度无损前提下，推理速度提升了5.88%～19.05%和45.45%～311.46%。     

一种新的云模型控制器设计

首先提出一种新型的云模型控制器结构模型．这种结构模型是一种本质非线性模型，可以很容易由一组不确定性推理规则构成．文中分析了云模型的非线性映射特性，同时给出了基于此结构模型的智能控制器的设计方法及仿真实例．     

范例推理在地理信息系统中的应用研究

范例推理（CBR）是一种用先前求解问题的经验和方法，通过类比和联想来解决当前相似问题的推理技术，它是动态决策环境下求解不良结构问题的常用方法。GIS系统作为一种新兴的地学工具，具有很强的空间分析能力，但由于地学问题的复杂性，一些地学现象很难用确切的模型进行模拟和预测。考虑到范例推理系统在处理半结构化和非结构化问题方面的出色能力，文中探讨了一个基于范例推理的GIS系统结构，并给出了地理范例的构建方法和表达模型。     

溯因推理研究：现状与问题

在人类认识世界的过程中,现实的生存世界里会不时发生着一些“令人惊奇的”现象,为了理解和分析这个问题,人们所使用的解疑释惑的方法往往就是尝试寻找引起这些现象的原因是什么。例如早上醒来你发现路是湿的,你会猜测昨晚天下雨了。通俗地讲这种解释观测事实(或已知结果)的推理过程就是溯因(Abduction)。可以说类似的例子一直在我们的日常生活或者科学研究中重复着,以现实生活中的医学诊断为例,当医生了解了患者的病症后,他会根据自己对疾病和症状间因果关系方面的医学知识,推断出可能的病因是什么。对于自然科学研究也是如此,N.R.Hanson和C.S.Pierce曾分别论证说,当开普勒断言“火星的运行轨迹是椭圆的”的时候,他所使用的推理方法就是溯因。     

An evolutionary algorithm for abductive reasoning

Abductive reasoning (or abduction) is the process of inferring hypotheses from observed data using a certain ‘knowledge’ encoded in the form of inference rules (or causal relations). Many important kinds of intellectual tasks, including medical diagnosis, fault diagnosis, scientific discovery, legal reasoning, and natural language understanding have been characterised as abduction. Unfortunately, abduction is 𝒩𝒫-hard. Genetic algorithms and biologically motivated computational paradigms inspired by the natural evolution turned out to be efficient in solving many hard problems while other existing approaches failed to solve in general. In this article, we present a genetic algorithm called HAKIM, for solving abduction problems. We encode an explanation in a chromosome-like structure, where every gene models a possible single hypothesis. Thereafter, we develop a fitness function that characterises the overall ‘quality’ of a chromosome representing an explanation; and then use standard genetic operators to compute a set of hypotheses that best explains the observed data. Simulation results on large-scale medical problems reveal the good performance of our model HAKIM.     

A Formal Model for Experience–Aided Diagnosis

This paper presents a novel approach to model–based diagnosis. The approach addresses the two main problems that have prevented model–based diagnostic techniques from being widely used: computational complexity of abduction and inadequacies of device models. A model for automated diagnosis is defined that combines (1) deduction to rule out hypotheses, (2) abduction to generate hypotheses, and (3) induction to recall past experiences and account for potential errors in the device models. A review of the three forms of inference is provided, as well as a detailed analysis of the relationship between case–based reasoning and induction. The proposed model for diagnosis is used to characterize diagnostic errors and relate them to different types of errors in the device models. Experimental results are then described and used to assert the practicality and the usefulness of the approach. The model presented in this paper yields a practical method for solving hard diagnostic problems at a reasonable computational cost and provides a theoretical basis for overcoming the problem of partially incorrect device models.     

Probabilistic Argumentation Systems and Abduction

Probabilistic argumentation systems are based on assumption-based reasoning for obtaining arguments supporting hypotheses and on probability theory to compute probabilities of supports. Assumption-based reasoning is closely related to hypothetical reasoning or inference through theory formation. The latter approach has well known relations to abduction and default reasoning. In this paper assumption-based reasoning, as an alternative to theory formation aiming at a different goal, will be presented and its use for abduction and model-based diagnostics will be explained. Assumption-based reasoning is well suited for defining a probability structure on top of it. On the base of the relationships between assumption-based reasoning on the one hand and abduction on the other hand, the added value introduced by probability into model based diagnostics will be discussed. Furthermore, the concepts of complete and partial models are introduced with the goal to study the quality of inference procedures. In particular this will be used to compare abductive to possible explanations.     

Abductive logics in a belief revision framework

Abduction was first introduced in the epistemological context of scientific discovery. It was more recently analyzed in artificial intelligence, especially with respect to diagnosis analysis or ordinary reasoning. These two fields share a common view of abduction as a general process of hypotheses formation. More precisely, abduction is conceived as a kind of reverse explanation where a hypothesis H can be abduced from events E if H is a good explanation of E. The paper surveys four known schemes for abduction that can be used in both fields. Its first contribution is a taxonomy of these schemes according to a common semantic framework based on belief revision. Its second contribution is to produce, for each non-trivial scheme, a representation theorem linking its semantic framework to a set of postulates. Its third contribution is to present semantic and axiomatic arguments in favor of one of these schemes, ordered abduction, which has never been vindicated in the literature.     

Solving abduction by computing joint explanations

An extension of abduction is investigated where explanations are jointly computed by sets of interacting agents. On the one hand, agents are allowed to partially contribute to the reasoning task, so that joint explanations can be singled out even if each agent does not have enough knowledge for carrying out abduction on its own. On the other hand, agents maintain their autonomy in choosing explanations, each one being equipped with a weighting function reflecting its perception about the reliability of sets of hypotheses. Given that different agents may have different and possibly contrasting preferences on the hypotheses to be chosen, some reasonable notions of agents’ agreement are introduced, and their computational properties are thoroughly studied. As an example application of the framework discussed in the paper, it is shown how to handle data management issues in Peer-to-Peer systems and, specifically, how to provide a repair-based semantics to inconsistent ones.      

CONSTRAINED RESOLUTION AND ABDUCTTVE TEMPORAL REASONING

This article presents our work on the effective implementation of abduction in temporal reasoning. This works builds on some results, both in the logic programming field and in the automated reasoning area. We have defined and implemented an abductive procedure, which is well adapted for temporal reasoning because it is based on a constrained resolution principle. Constrained resolution has two advantages for temporal reasoning: First, it allows us to deal efficiently with temporal ordering and equality predicates, which are otherwise too much trouble with classical resolution; second, it allows a restricted form of abduction where hypotheses are limited to ordering relationships. From the logic programming area, our work uses results and procedures developed by others in the abductive logic programming field. The procedure we define and implement in this work is relatively independent of the temporal formalism: It has been used with some reified temporal logics and with the event calculus. More generally it can be used on any point-based temporal formalism, provided that a correct and complete algorithm is available for checking the consistency of a set of temporal ordering relationships in this language.     

An efficient LP-based admissible heuristic for cost-based abduction

Cost-based abduction (CBA) is an important problem in reasoning under uncertainty. The CBA problem is NP-hard, and existing techniques have exponential worst-case complexity. This paper presents an admissible heuristic for CBA based on the use of linear programming to obtain an optimistic estimate of the cost-to-goal. The article then presents empirical results that indicate that the authors' method is efficient in comparison to Santos‘ integer linear programming method.     

The synthesis of cognitive procedures and the problem of induction

The JSM-method of automated hypotheses generation realizing the automated plausible reasoning in Intelligent Systems is described. It is shown that the method represents specially organized interaction of induction, analogy and abduction. The foundations of exact epistemology for JSM- Intelligent Systems are formulated.