Browsing by Author "Law, Mark"

Sort by: Order: Results:

  • FastLAS: scalable inductive logic programming incorporating domain-specific optimisation criteria
    Law, Mark; Russo, Alessandra; Bertino, Elisa; Broda, Krysia; Lobo, Jorge (Association for the Advancement of Artificial Intelligence (AAAI), 2020)
    Inductive Logic Programming (ILP) systems aim to find a set of logical rules, called a hypothesis, that explain a set of examples. In cases where many such hypotheses exist, ILP systems often bias towards shorter solutions, ...
  • FFNSL: Feed-Forward Neural-Symbolic Learner
    Cunnington, Daniel; Law, Mark; Lobo, Jorge; Russo, Alessandra (Springer, 2023)
    Logic-based machine learning aims to learn general, interpretable knowledge in a data-efficient manner. However, labelled data must be specified in a structured logical form. To address this limitation, we propose a ...
  • Induction and exploitation of subgoal automata for reinforcement learning
    Furelos Blanco, Daniel; Law, Mark; Jonsson, Anders, 1973-; Broda, Krysia; Russo, Alessandra (AI Access Foundation, 2021)
    In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks. ISA interleaves reinforcement learning with the induction of a subgoal automaton, an automaton ...
  • Online symbolic learning of policies for explainable security
    Drozdov, Arthur; Law, Mark; Lobo, Jorge; Russo, Alessandra; Wilathgamuwage Don, Mercion (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Statistical Machine Learning (ML) has been proved to be an invaluable tool in many areas including privacy and security. On the other hand, recent advances in the field of Symbolic Learning have included novel scalable ...
  • Representing and learning grammars in answer set programming
    Law, Mark; Russo, Alessandra; Bertino, Elisa; Broda, Krysia; Lobo, Jorge (Association for the Advancement of Artificial Intelligence (AAAI), 2019)
    In this paper we introduce an extension of context-free grammars called answer set grammars (ASGs). These grammars allow annotations on production rules, written in the language of Answer Set Programming (ASP), which can ...