Incremental learning of event definitions with Inductive Logic Programming

@article{Katzouris2015IncrementalLO,
  title={Incremental learning of event definitions with Inductive Logic Programming},
  author={Nikos Katzouris and A. Artikis and Georgios Paliouras},
  journal={Machine Learning},
  year={2015},
  volume={100},
  pages={555-585}
}
Event recognition systems rely on knowledge bases of event definitions to infer occurrences of events in time. Using a logical framework for representing and reasoning about events offers direct connections to machine learning, via Inductive Logic Programming (ILP), thus allowing to avoid the tedious and error-prone task of manual knowledge construction. However, learning temporal logical formalisms, which are typically utilized by logic-based event recognition systems is a challenging task… 
Online learning of event definitions
TLDR
A decoupling scheme of the Event Calculus axioms during the learning process is employed, that allows to learn each clause in isolation, and abductive-inductive logic programming techniques to handle unobserved target predicates.
Parallel Online Learning of Event Definitions
TLDR
This work presents a version of OLED that allows for parallel, online learning and evaluates the approach on a benchmark activity recognition dataset and shows that it can reduce training times, while achieving super-linear speed-ups on some occasions.
Distributed Online Learning of Event Definitions
TLDR
This work presents a version of OLED that allows for distributed, online learning, and shows that it can significantly reduce training times, exchanging minimal information between processing nodes.
Online Learning of Weighted Relational Rules for Complex Event Recognition
TLDR
This work combines an existing online algorithm for learning crisp relational structure with an online method for weight learning in Markov Logic Networks (MLN) to create an algorithm that learns complex event patterns in the form of Event Calculus theories in the MLN semantics.
Online Learning Probabilistic Event Calculus Theories in Answer Set Programming
TLDR
This paper presents a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of weighted rules in the Event Calculus, whose structure and weights are learnt online.
WOLED: A tool for Online Learning Weighted Answer Set Rules for Temporal Reasoning Under Uncertainty
TLDR
WOLED is presented, a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of weighted rules in the Event Calculus, whose structure and weights are learnt online.
Logic-Based Online Complex Event Rule Learning with Weight Optimization
TLDR
This work proposes a method based on root mean square prop (RMSprop), a weight learning method to improve the original algorithm, and optimize the weight of the rule structure, and combine the existing rule structure learning method and weightlearning method to learn rules.
Learning & Reasoning for Logic-Based Complex Event Recognition
TLDR
This short paper focuses on logic-based methods for CER, which are of special interest thanks to their formal semantics and their direct connections to uncertainty handling and machine learning via Statistical Relational Learning and Inductive Logic Programming.
Event Recognition Under Uncertainty and Incomplete Data
TLDR
This thesis addresses the issue of uncertainty in logic-based event recognition by extending the Event Calculus with probabilistic reasoning, and shows how and under what assumptions the proposed model can overcome these problems.
Reactive Reasoning with the Event Calculus
TLDR
RTEC is an Event Calculus dialect with novel implementation and 'windowing' techniques that allow for efficient event recognition, scalable to large data streams, and is capable of meeting the performance requirements identified in a recent survey of event processing use cases.
...
...

References

SHOWING 1-10 OF 120 REFERENCES
Logic-based representation, reasoning and machine learning for event recognition
TLDR
Representative approaches of logic-based event recognition are reviewed, open research issues of this field are discussed, and they are supported by machine learning tools automating the construction and refinement of event structures.
A logic-based calculus of events
We outline an approach for reasoning about events and time within a logic programming framework. The notion of event is taken to be more primitive than that of time and both are represented
Logic-based event recognition
TLDR
This paper reviews representative approaches of logic-based event recognition and illustrates the reviewed approaches with the use of a real-world case study: event recognition for city transport management.
Scaling Up Inductive Logic Programming by Learning from Interpretations
TLDR
This paper relates the setting to propositional data mining and to the classical ILP setting, and shows that learning from interpretations corresponds to learning from multiple relations and thus extends the expressiveness of propositional learning, while maintaining its efficiency to a large extent.
An Event Calculus for Event Recognition
TLDR
The evaluation shows that RTEC can support real-time event recognition and is capable of meeting the performance requirements identified in a survey of event processing use cases.
Interleaved Inductive-Abductive Reasoning for Learning Event-Based Activity Models
TLDR
An interleaved inductive-abductive model for reasoning about complex spatio-temporal narratives is proposed and applied to an airport domain consisting of video data for 10 turn-arounds.
Inductive Logic Programming: Theory and Methods
Nonmonotonic abductive inductive learning
  • O. Ray
  • Computer Science
    J. Appl. Log.
  • 2009
Hybrid Abductive Inductive Learning: A Generalisation of Progol
TLDR
This paper exposes a previously unknown incompleteness of Progol5 with respect to Bottom Generalisation, and proposes a new approach, called Hybrid Abductive Inductive Learning, that integrates the ILP principles of progol 5 with Abductives Logic Programming (ALP).
Theory Completion Using Inverse Entailment
TLDR
A general ILP technique called "Theory Completion using Inverse Entailment" (TCIE) is introduced which is applicable to non-OPL applications and is closely allied to abductive inference.
...
...