Výsledky vyhľadávania - "INDUCTIVE logic programming"

Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP Autor Muggleton, Stephen H., Schmid, Ute, Zeller, Christina, Tamaddoni-Nezhad, Alireza, Besold, Tarek

“…During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated…”
Získať plný text

A Critical Review of Inductive Logic Programming Techniques for Explainable AI Autor Zhang, Zheng, Yilmaz, Levent, Liu, Bo

“…Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption. To…”
Získať plný text

Inductive general game playing Autor Cropper, Andrew, Evans, Richard, Law, Mark

“…General game playing (GGP) is a framework for evaluating an agent’s general intelligence across a wide range of tasks. In the GGP competition, an agent is…”
Získať plný text

Fast rule mining in ontological knowledge bases with AMIE Autor Galárraga, Luis, Teflioudi, Christina, Hose, Katja, Suchanek, Fabian M.

“…Recent advances in information extraction have led to huge knowledge bases (KBs), which capture knowledge in a machine-readable format. Inductive logic…”
Získať plný text

Logical reduction of metarules Autor Cropper, Andrew, Tourret, Sophie

“…Many forms of inductive logic programming (ILP) use metarules , second-order Horn clauses, to define the structure of learnable programs and thus the…”
Získať plný text

Propositionalization and embeddings: two sides of the same coin Autor Lavrač, Nada, Škrlj, Blaž, Robnik-Šikonja, Marko

“…Data preprocessing is an important component of machine learning pipelines, which requires ample time and resources. An integral part of preprocessing is data…”
Získať plný text

A differentiable first-order rule learner for inductive logic programming Autor Gao, Kun, Inoue, Katsumi, Cao, Yongzhi, Wang, Hanpin

“…Learning first-order logic programs from relational facts yields intuitive insights into the data. Inductive logic programming (ILP) models are effective in…”
Získať plný text

Learning programs by learning from failures Autor Cropper, Andrew, Morel, Rolf

“…We describe an inductive logic programming (ILP) approach called learning from failures . In this approach, an ILP system (the learner) decomposes the learning…”
Získať plný text

Inductive logic programming at 30 Autor Cropper, Andrew, Dumančić, Sebastijan, Evans, Richard, Muggleton, Stephen H.

“…Inductive logic programming (ILP) is a form of logic-based machine learning. The goal is to induce a hypothesis (a logic program) that generalises given…”
Získať plný text

GenEth: a general ethical dilemma analyzer Autor Anderson, Michael, Anderson, Susan Leigh

“…We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists…”
Získať plný text

Meta-Interpretive Learning from noisy images Autor Muggleton, Stephen, Dai, Wang-Zhou, Sammut, Claude, Tamaddoni-Nezhad, Alireza, Wen, Jing, Zhou, Zhi-Hua

“…Statistical machine learning is widely used in image classification. However, most techniques (1) require many images to achieve high accuracy and (2) do not…”
Získať plný text

Best-effort inductive logic programming via fine-grained cost-based hypothesis generation: The inspire system at the inductive logic programming competition Autor Schüller, Peter, Benz, Mishal

“…We describe the Inspire system which participated in the first competition on inductive logic programming (ILP). Inspire is based on answer set programming…”
Získať plný text

αILP: thinking visual scenes as differentiable logic programs Autor Shindo, Hikaru, Pfanschilling, Viktor, Dhami, Devendra Singh, Kersting, Kristian

“…Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs…”
Získať plný text

Lifted discriminative learning of probabilistic logic programs Autor Nguembang Fadja, Arnaud, Riguzzi, Fabrizio

“…Probabilistic logic programming (PLP) provides a powerful tool for reasoning with uncertain relational models. However, learning probabilistic logic programs…”
Získať plný text

Common abductive explanations in first order logic Autor Rouveirol, Céline, Soldano, Henry, Kazi Aoual, Malik, Ventos, Véronique

“…We build upon a recent definition of a common explanation for the label shared by a group of observations. The motivation stems from explaining how a specific…”
Získať plný text

The Daikon system for dynamic detection of likely invariants Autor Ernst, Michael D., Perkins, Jeff H., Guo, Philip J., McCamant, Stephen, Pacheco, Carlos, Tschantz, Matthew S., Xiao, Chen

“…Daikon is an implementation of dynamic detection of likely invariants; that is, the Daikon invariant detector reports likely program invariants. An invariant…”
Získať plný text

FFNSL: Feed-Forward Neural-Symbolic Learner Autor Cunnington, Daniel, Law, Mark, Lobo, Jorge, Russo, Alessandra

“…Logic-based machine learning aims to learn general, interpretable knowledge in a data-efficient manner. However, labelled data must be specified in a…”
Získať plný text

Beneficial and harmful explanatory machine learning Autor Ai, Lun, Muggleton, Stephen H., Hocquette, Céline, Gromowski, Mark, Schmid, Ute

“…Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A…”
Získať plný text

Constructing generative logical models for optimisation problems using domain knowledge Autor Srinivasan, Ashwin, Vig, Lovekesh, Shroff, Gautam

“…In this paper we seek to identify data instances with a low value of some objective (or cost) function. Normally posed as optimisation problems, our interest…”
Získať plný text

On the non-efficient PAC learnability of conjunctive queries Autor ten Cate, Balder, Funk, Maurice, Jung, Jean Christoph, Lutz, Carsten

“…This note serves three purposes: (i) we provide a self-contained exposition of the fact that conjunctive queries are not efficiently learnable in the…”
Získať plný text