Ethical Decision-Making Framework Based on Incremental ILP Considering Conflicts

Humans are experiencing the inclusion of artificial agents in their lives,such as unmanned vehicles,service robots,voice assistants,and intelligent medical care.If the artificial agents cannot align with social values or make ethical decisions,they may not meet the expectations of humans.Traditionally,an ethical decision-making framework is constructed by rule-based or statistical approaches.In this paper,we propose an ethical decision-making framework based on incremental ILP(Inductive Logic Programming),which can overcome the brittleness of rule-based approaches and little interpretability of statistical approaches.As the current incremental ILP makes it difficult to solve conflicts,we propose a novel ethical decision-making framework considering conflicts in this paper,which adopts our proposed incremental ILP system.The framework consists of two processes:the learning process and the deduction process.The first process records bottom clauses with their score functions and learns rules guided by the entailment and the score function.The second process obtains an ethical decision based on the rules.In an ethical scenario about chatbots for teenagers’mental health,we verify that our framework can learn ethical rules and make ethical decisions.Besides,we extract incremental ILP from the framework and compare it with the state-of-the-art ILP systems based on ASP(Answer Set Programming)focusing on conflict resolution.The results of comparisons show that our proposed system can generate better-quality rules than most other systems.

Carnap＇s Thought on Inductive Logic

Although we often see references to Carnap＇s inductive logic even in modern literatures, seemingly its confusing style has long obstructed its correct understanding. So instead of Carnap, in this paper, I devote myself to its necessary and sufficient commentary. In the beginning part （Sections 2-5）, I explain why Carnap began the study of inductive logic and bow he related it with our thought on probability （Sections 2-4）. Therein, I trace Carnap＇s thought back to Wittgenstein＇s Tractatus as well （Section 5）. In the succeeding sections, I attempt the simplest exhibition of Carnap＇s earlier system, where his original thought was thoroughly provided. For this purpose, minor concepts to which researchers have not paid attention are highlighted, for example, m-function （Section 8）, in-correlation （Section 10）, C-correlate （Section 10）, statistical distribution （Section 12）, and fitting sequence （Section 17）. The climax of this paper is the proof of theorem （56）. Through this theorem, we will be able to overview Carnap＇s whole system.

A DELTA INFERENCE OPERATOR FOR REASONABLE CONSEQUENCE RELATION

This paper determines a delta inference operator C based on the notion of reasonable consequence of Adams′ system and studies its properties. It shows another approach to study inductive and probabilistic reasoning.

Causal association rule mining methods based on fuzzy state description

Aiming at the research that using more new knowledge to develope knowledge system with dynamic accordance, and under the background of using Fuzzy language field and Fuzzy language values structure as description framework, the generalized cell Automation that can synthetically process fuzzy indeterminacy and random indeterminacy and generalized inductive logic causal model is brought forward. On this basis, a kind of the new method that can discover causal association rules is provded. According to the causal information of standard sample space and commonly sample space, through constructing its state （abnormality） relation matrix, causal association rules can be gained by using inductive reasoning mechanism. The estimate of this algorithm complexity is given,and its validiw is proved through case.

Identification of Tumor Evolution Patterns by Means of Inductive Logic Programming

In considering key events of genomic disorders in the development and progression of cancer, the correlation between genomic instability and carcinogenesis is currently under investigation. In this work, we propose an inductive logic programming approach to the problem of modeling evolution patterns for breast cancer. Using this approach, it is possible to extract fingerprints of stages of the disease that can be used in order to develop and deliver the most adequate therapies to patients. Furthermore, such a model can help physicians and biologists in the elucidation of molecular dynamics underlying the aberrations-waterfall model behind carcinogenesis. By showing results obtained some hints about further approach to the hypotheses. on a real-world dataset, we try to give knowledge-driven validations of such

An Efficient Multiple Predicate Learner

In this papers we examine the issue of learning multiple predicates from given training examples. A proposed MPL-CORE algorithm efficiently induces Horn clauses from examples and background knowledge by employing a single predicate learning module CORE. A fast failure mechanism is also proposed which contributes learning efficiency and learnability to the algorithm. MPL-CORE employs background knowledge that can be represented in intensional (Horn clauses) or extensional (ground atoms) forms during its learning process. With the fast failure mechanism, MPL-CORE outperforms previous multiple predicate learning systems in both the computational complexity and learnability.

DLP Learning from Uncertain Data

Description logic programs （DLP） are an expressive but tractable subset of OWL. This paper ana-lyzes the important under-researched problem of learning DLP from uncertain data. Current studies have rarely explored the plentiful uncertain data populating the semantic web. This algorithm handles uncertain data in an inductive logic programming framework by modifying the performance evaluation criteria. A pseudo-log-likelihood based measure is used to evaluate the performance of different literals under uncer-tainties. Experiments on two datasets demonstrate that the approach is able to automatically learn a rule-set from uncertain data with acceptable accuracy.