An interesting feature that traditional approaches to inductive logic programming are missing is the ability to treat noisy and non-logical data. Neural-symbolic approaches to inductive logic programming have been rec...
详细信息
ISBN:
(纸本)9783031157073;9783031157066
An interesting feature that traditional approaches to inductive logic programming are missing is the ability to treat noisy and non-logical data. Neural-symbolic approaches to inductive logic programming have been recently proposed to combine the advantages of inductive logic programming, in terms of interpretability and generalization capability, with the characteristic capacity of deep learning to treat noisy and nonlogical data. This paper concisely surveys and briefly compares three promising neural-symbolic approaches to inductive logic programming that have been proposed in the last five years. The considered approaches use Datalog dialects to represent background knowledge, and they are capable of producing reusable logical rules from noisy and non-logical data. Therefore, they provide an effective means to combine logical reasoning with state-of-the-art machine learning.
Grammars have been used for the formal specification of programming languages [1], and there are a number of commercial products which now use grammars. However, these have tended to be focused mainly on flow control ...
详细信息
ISBN:
(纸本)0819449547
Grammars have been used for the formal specification of programming languages [1], and there are a number of commercial products which now use grammars. However, these have tended to be focused mainly on flow control type applications. In this paper, we consider the potential use of picture grammars and inductive logic programming in generic image understanding applications, such as object recognition. A number of issues are considered, such as what type of grammar needs to be used, how to construct the grammar with its associated attributes, difficulties encountered with parsing grammars followed by issues of automatically learning grammars using a genetic algorithm. The concept of inductive logic programming is then introduced as a method that can overcome some of the earlier difficulties.
We present a relational multi-agent reinforcement learning algorithm in which two agents work together to achieve a goal in an environment represented by structured entities and relations. Our proposal takes a hybrid ...
详细信息
ISBN:
(数字)9783031159312
ISBN:
(纸本)9783031159312;9783031159305
We present a relational multi-agent reinforcement learning algorithm in which two agents work together to achieve a goal in an environment represented by structured entities and relations. Our proposal takes a hybrid connectionist-symbolic approach, where a classical actorcritic method with an iterative weight update scheme is used to guide the derivation of an agent's policy, which is purely expressed as first-order logic. A recent technique, differentiable inductive logic programming, is applied to integrate these two parts into a trainable system. We tailor the centralized training with decentralized execution framework to meet the symbolic-represented underlying structure. Agents are designed to communicate with one another in terms of logical predicates to alleviate the partially observable problem prevalent in the multi-agent setting. Empirical studies on the classical grid-world task demonstrate that the proposed method can learn close to optimal strategies and has better interpretability than traditional reinforcement learning approaches.
Relation Extraction ( RE) is the task of detecting semantic relations between entities in text. Most of the state-of-the-art RE systems rely on statistical machine learning techniques which usually employ an attribute...
详细信息
ISBN:
(纸本)9781509001637
Relation Extraction ( RE) is the task of detecting semantic relations between entities in text. Most of the state-of-the-art RE systems rely on statistical machine learning techniques which usually employ an attribute-value representation of features. Contrarily to this trend, we focus on an alternative approach to RE based on the automatic induction of symbolic extraction rules. We present OntoILPER, an RE system based on inductive logic programming which uses a domain ontology in its extraction process. Several experiments are discussed in this paper over the reACE 2004/2005 reference corpora. The results are encouraging and seem to demonstrate the effectiveness of the proposed solution.
Software libraries organize useful functionalities in order to promote modularity and code reuse. A typical library is used by client programs through an application programming interface (API) that hides its internal...
详细信息
ISBN:
(纸本)9781605580791
Software libraries organize useful functionalities in order to promote modularity and code reuse. A typical library is used by client programs through an application programming interface (API) that hides its internals from the client. Typically, the rules governing the correct usage of the API are documented informally. In many cases, libraries may have complex API usage rules and unclear documentation. As a result, the behaviour of the library under some corner cases may not be well understood by the programmer. Formal specifications provide a precise understanding of the API behaviour. We propose a methodology for learning interface specifications using inductive logic programming (ILP). Our technique runs several unit. tests on the library in order to generate relations describing the operation of the library. The data collected from these tests are used by an inductive learner to obtain rich Datalog/Prolog specifications. Such specifications capture essential properties of interest to the user. They may be used for applications such as reverse engineering the library internals or constructing checks on the application code to enforce proper API usage along with other properties of interest.
This paper presents an approach to infer UI patterns existent in a web application. This reverse engineering process is performed in two steps. First, execution traces are collected from user interactions using the Se...
详细信息
ISBN:
(纸本)9789899843400
This paper presents an approach to infer UI patterns existent in a web application. This reverse engineering process is performed in two steps. First, execution traces are collected from user interactions using the Selenium software. Second, the existing UI patterns within those traces are identified using Machine Learning inference with the Aleph ILP system. The paper describes and illustrates the proposed methodology on a case study over the Amazon web site.
Artificial society is a discipline to study mechanisms of social system and phenomena which the mechanisms make. Emergence is global phenomena occurred by local mechanisms, such as, by collective behavior of autonomou...
详细信息
ISBN:
(纸本)9781479941735
Artificial society is a discipline to study mechanisms of social system and phenomena which the mechanisms make. Emergence is global phenomena occurred by local mechanisms, such as, by collective behavior of autonomous agents. Understanding of emergence phenomena is a challenging subject. In this paper we use the framework of inductive logic programming (ILP) for artificial society and emergence behavior study. ILP is a branch of machine learning based on logicprogramming and inductive inference. We investigate the possibility of ILP in artificial society study. ILP and logicprogramming technique are applied to representation of an artificial society model, called Sugarscape, and to rule learning for agent behavior. Although classical ILP algorithms target classification problems, the proposed algorithm grows behavior rule for an evaluation measurement. Phenomena which this paper treate is limited but we showed that ILP technique can be applied to study in the field of artificial society.
A new genetic inductive logic programming (GILP for short) algorithm named PT-NFF-GILP (Phase Transition and New Fitness Function based Genetic inductive logic programming) is proposed in this paper. Based on phase tr...
详细信息
ISBN:
(纸本)9781467315098
A new genetic inductive logic programming (GILP for short) algorithm named PT-NFF-GILP (Phase Transition and New Fitness Function based Genetic inductive logic programming) is proposed in this paper. Based on phase transition of the covering test, PT-NFF-GILP randomly generates initial population in phase transition region instead of the whole space of candidate clauses. Moreover, a new fitness function, which not only considers the number of examples covered by rules, but also considers the ratio of the examples covered by rules to the training examples, is defined in PT-NFF-GILP. The new fitness function measures the quality of first-order rules more precisely, and enhances the search performance of algorithm. Experiments on ten learning problems show that: 1) the new method of generating initial population can effectively reduce iteration number and enhance predictive accuracy of GILP algorithm;2) the new fitness function measures the quality of first-order rules more precisely and avoids generating over-specific hypothesis;3) The performance of PT-NFF-GILP is better than other algorithms compared with it, such as G-NET, KFOIL and NFOIL.
Rule based machine translation systems face different challenges in building the translation model in a form of transfer rules. Some of these problems require enormous human effort to state rules and their consistency...
详细信息
ISBN:
(纸本)9781424445387
Rule based machine translation systems face different challenges in building the translation model in a form of transfer rules. Some of these problems require enormous human effort to state rules and their consistency. This is where different human linguists make different rules for the same sentence. A human linguist states rules to be understood by human rather than machines. The proposed translation model (from Arabic to English) tackles the mentioned problem of building translation model. This model employs inductive logic programming (ILP) to learn the language model from a set of example pairs acquired from parallel corpora and represent the language model in a rule-based format that maps Arabic sentence pattern to English sentence pattern. By testing the model on a small set of data, it generated translation rules with logarithmic growing rate and with word error rate 11%
Grid computing systems are extremely large and complex so, manually dealing with its failures becomes impractical. Recently, it has been proposed that the systems themselves should manage their own failures or malfunc...
详细信息
ISBN:
(纸本)9781424450824
Grid computing systems are extremely large and complex so, manually dealing with its failures becomes impractical. Recently, it has been proposed that the systems themselves should manage their own failures or malfunctions. This is referred as self-healing. To deal with this challenging, is required to predict and control the process through a number of automated learning and proactive actions. In this paper, we proposed inductive logic programming, a relational machine learning method, for prediction and root causal analysis that makes it possible the development of a self-healing component.
暂无评论