At ILASP, we build logic-based machine learning systems, which have several advantages over other forms of machine learning.
Interpretability
The learned knowledge can be translated into English, meaning that it can be explained to users and verified or corrected where necessary.
Use of existing knowledge
Logic-based systems do not need to learn everything from scratch, and can instead start from an existing knowledge base, containing anything known before the learning starts or even previously learned rules.
Generalisation
Logic-based systems can generalise from very few examples, making it possible to learn complex knowledge without needing large datasets.
Our Customers and Collaborators
Example applications of ILASP's systems
Event Detection
ILASP can be used to detect events of interest in pre-processed streams of images. Pre-processing is necessary to convert unstructured image data into the more structured form, consisting of the coordinates of various objects, that can be used by ILASP. The pre-processing can be performed using off-the-shelf techniques.
Planning and Learning to Plan
ILASP systems can be used both to generate new plans and correct existing plans mid-execution. In recent work for the RAF's Air Information eXperimentation Laboratory, we have been developing planning systems to aid Command and Control (C2).
Anomaly Detection
ILASP systems can be used both to learn rules which apply to most of the data in a dataset. The resulting rules can then be used both to identify anomalous datapoints, and also to act as a filter to flag incorrect new data before it is added.
User Preference Learning
ILASP has been used to learn users' individual preferences (both from real and from synthetic data); for example, ILASP can learn to predict a user's preferred schedule, car, journey or type of sushi. Unlike many other preference learning techniques, ILASP's ability to learn from very few examples enables it to learn highly customised preferences from a single user.
Sentence Chunking
Sentence chunking is the task of splitting a sentence into its main chunks. As sentences are unstructured data, in order to use a logic-based system, the sentences are processed using the Stanford CoreNLP library, converting each sentence into a set of Part Of Speech tags. This application shows how logic-based systems can be combined with non-logic-based systems such as CoreNLP to further expand the potential application domains.
ILASP systems are designed to be general-purpose, meaning that they can be applied to many different domains. You can find further examples in our research papers.
About us
The first three versions of the ILASP system were developed as part of Mark Law's PhD, while he was studying in the Department of Computing at Imperial College London. Since then, Mark established ILASP Limited, with the dual aims of demonstrating real-world applications of logic-based learning systems, and of continuing to further the fundamental research.
Meet our team →
Dr Mark Law
Director and Senior Research Scientist
Honorary Research Fellow, Imperial College London
Lucy Law
Director
Professor Alessandra Russo
Senior Research Scientist
Head of the Department of Computing, Imperial College London
Dr Bashir Mitchell
Research Scientist
Matthew Tait
Research Scientist
Joe Jenner-Bailey
Junior Research Scientist
Chloé Silva
Junior Research Scientist
Watch our introduction video
Our main system, ILASP (Inductive Learning of Answer Set Programs), which gave the company its name, learns knowledge expressed in the language of Answer Set Programming (ASP). ILASP's ability to learn full ASP programs, compared with previous approaches that could only learn a very restricted subset of ASP, has opened up a variety of new applications that were previously out of scope for Logic-based Machine Learning systems.