ILASP

Nearby engineering companies

Dann Developments
Autumn Park Business Centre, Dysart Road

Very pleased to share our paper on "Search Space Expansion for Efficient Incremental Inductive Logic Programming from Streamed Data", which was presented by Mark Law at IJCAI-22 last week. This was joint work with Krysia Broda and Alessandra Russo from Imperial College London.

https://www.ijcai.org/proceedings/2022/0374

Search Space Expansion for Efficient Incremental Inductive Logic Programming from Streamed Data | IJCAI Electronic proceedings of IJCAI 2022

25/01/2022

We're hiring! If you are interested in applying for a role as a Junior Research Scientist, please email [email protected]. For full details of the job, please see https://www.linkedin.com/jobs/view/2893656084/.

19/10/2021

We are pleased to announce that ILASP is now officially based in Grantham. We have moved into the Autumn Park Business Centre on Dysart Road.

08/10/2021

ILASP updated their address.

Logic based learning of Answer Set Programs Tutorial

20/09/2021

The tutorial in this video will be available as part of the Autumn School on Logic and Constraint Programming, which will take place during the 37th International Conference on Logic Programming (ICLP) (September 20-27, 2021, online). The tutorial is split into two parts: Part I will be a live tutorial given by Professor Alessandra Russo; and Part II is the recording in this video, given by Mark Law.

https://www.youtube.com/watch?v=9LdkajKN8KE&t=8s

Logic based learning of Answer Set Programs Tutorial This tutorial will be available as part of the Autumn School on Logic and Constraint Programming, which will take place during the 37th International Confere...

13/04/2021

We are delighted to announce that, this month, ILASP has started a new contract with the Air Information Experimentation (AiX) Laboratory of the RAF Rapid Capabilities Office and SiXworks Limited. The project will investigate the use of explainable machine learning for automated decision-making.

29/08/2020

This video shows ILASP being applied to the task of event detection, where the goal is to learn rules that can automatically detect pairs of people meeting in video streams. The rules that ILASP learns are automatically translated into plain English. The dataset used in this video comes from the EC Funded CAVIAR project/IST 2001 37540, available at http://homepages.inf.ed.ac.uk/rbf/CAVIAR/.

21/06/2020

We are delighted to announce that ILASP version 4 has just been released (https://github.com/marklaw/ILASP-releases/releases/tag/v4.0.0). In addition to a new faster conflict-driven method for ILP, ILASP4 now supports user-customisation of the learning process by using the new PyLASP scripts (www.ilasp.com/PyLASP). More information on the technical details will be made available in the coming weeks.

The ILASP System for Inductive Learning of Answer Set Programs – Association for Logic Programming

06/05/2020

Thank you to the Association of Logic Programming for the invitation to write an article on the ILASP system for the ALP newsletter. This article provides an introduction to ILASP's learning framework and an overview of the various ILASP algorithms. The article also discusses some of the more recent advances, and what is planned for ILASP4.

https://www.cs.nmsu.edu/ALP/2020/04/the-ilasp-system-for-inductive-learning-of-answer-set-programs/

The ILASP System for Inductive Learning of Answer Set Programs – Association for Logic Programming ALP ISSUE, Feature Articles The ILASP System for Inductive Learning of Answer Set Programs by Editors • April 30, 2020 • 0 Comments By Mark Law, Alessandra Russo, Krysia BrodaILASP Limited and Department of Computing, Imperial College London, UK Abstract The goal of Inductive Logic Progr...

23/03/2020

Logic-based machine learning systems learn highly general rules, which can then be applied on new similar tasks, without the need for retraining.

10/03/2020

Logic-based machine learning has significant advantages over other forms of machine learning.

05/03/2020

Artificial Intelligence (AI) may one day have a massive impact on all of our lives. In particular, Machine Learning has huge potential, by allowing AI systems to improve over time as they observe more and more data; however, many current forms of Machine Learning are not interpretable, meaning that it is impossible to understand (or question) the decisions they make. This can make applying Machine Learning to everyday problems quite frustrating. Imagine, for example, being wrongly denied an insurance policy or a loan with no explanation.

At ILASP, we build Logic-based Machine Learning systems, which learn highly expressive rules that can be translated into plain English. This makes it possible to provide simple explanations of the reasons behind decision making.