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...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.展开更多
Inductive logic programming adopts the standard horn lope program as its logic framework for inductivelearning. Due to the fact, however, that the expressive power of horn logic is relatively limited and the mechansm ...Inductive logic programming adopts the standard horn lope program as its logic framework for inductivelearning. Due to the fact, however, that the expressive power of horn logic is relatively limited and the mechansm ofnegation is mostly that of negation as failure, it is difficult to make full use of negative information and consequentlynot suitable for inductive learning. This Paper adopts nounal lope program as me language of inductive logic programsand presents accordingly a kind of semantics called Limited Negation semantics. The issues of direct denotation andinference of negation in concept induction are solved. The paper shows that LN is directly generalized for the semantics of Well-Founded in die significance Of optional negation and has superior theoretical features, especially the capability Of expressing and processing negation by introducing the constant ’false’. ExperimentS also show that the inductive concepts in learning are accurately interpreted with LN.展开更多
The Learning method of inductive logic programming evaluates the the quality of inductive hypotheses commonlyby how well the hypotheses cover training examples extensionally. Ths kind of evalution will be completely i...The Learning method of inductive logic programming evaluates the the quality of inductive hypotheses commonlyby how well the hypotheses cover training examples extensionally. Ths kind of evalution will be completely inapplica-ble to the situation where there are non-simple or noise examples. Based on Limited Negative semantics, This paperextends induction of simple examples to that of generalized ones and presents 3 criteria on accepting inductive hypothe-ses in order to fit for different goals of induction. The relation between inductive hypotheses and background knowledgeis also established in this Paper. The conclusions in this paper are helpful to implement learning algorithms and to ex-tend application fields of ILP.展开更多
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...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展开更多
The notion of abduction was first introduced by the philosopher and logician C. S. Pierce, who claims de-duction, abduction and induction are three different forms of human reasoning. Broadly speaking, abduction is a ...The notion of abduction was first introduced by the philosopher and logician C. S. Pierce, who claims de-duction, abduction and induction are three different forms of human reasoning. Broadly speaking, abduction is a rea-soning process invoked to explain a puzzling observation. The study of logic-based abduction has been the most activeresearch in AI, and there are many results around the subject. This paper surveys the state-of-the-art research andpresents some problems for future work.展开更多
基金This work was funded by the National Natural Science Foundation of China Nos.U22A2099,61966009,62006057the Graduate Innovation Program No.YCSW2022286.
文摘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.
文摘Inductive logic programming adopts the standard horn lope program as its logic framework for inductivelearning. Due to the fact, however, that the expressive power of horn logic is relatively limited and the mechansm ofnegation is mostly that of negation as failure, it is difficult to make full use of negative information and consequentlynot suitable for inductive learning. This Paper adopts nounal lope program as me language of inductive logic programsand presents accordingly a kind of semantics called Limited Negation semantics. The issues of direct denotation andinference of negation in concept induction are solved. The paper shows that LN is directly generalized for the semantics of Well-Founded in die significance Of optional negation and has superior theoretical features, especially the capability Of expressing and processing negation by introducing the constant ’false’. ExperimentS also show that the inductive concepts in learning are accurately interpreted with LN.
文摘动作模型学习可以使Agent主动适应动态环境中的变化,从而提高Agent的自治性,同时也可为动态域建模提供一个初步模型,为后期的模型完善和修改提供了基础。通过结合归纳逻辑程序设计(Inductive Logic Programming,ILP)和回答集程序设计(Answer Set Programming,ASP),设计了一个学习B语言描述的动作模型算法,该算法可以在混合规模的动态域中进行学习,并采用经典规划实例验证了该学习算法的有效性。
文摘The Learning method of inductive logic programming evaluates the the quality of inductive hypotheses commonlyby how well the hypotheses cover training examples extensionally. Ths kind of evalution will be completely inapplica-ble to the situation where there are non-simple or noise examples. Based on Limited Negative semantics, This paperextends induction of simple examples to that of generalized ones and presents 3 criteria on accepting inductive hypothe-ses in order to fit for different goals of induction. The relation between inductive hypotheses and background knowledgeis also established in this Paper. The conclusions in this paper are helpful to implement learning algorithms and to ex-tend application fields of ILP.
文摘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
文摘The notion of abduction was first introduced by the philosopher and logician C. S. Pierce, who claims de-duction, abduction and induction are three different forms of human reasoning. Broadly speaking, abduction is a rea-soning process invoked to explain a puzzling observation. The study of logic-based abduction has been the most activeresearch in AI, and there are many results around the subject. This paper surveys the state-of-the-art research andpresents some problems for future work.
