For my full publication record, please see my CV
1. The Development of Automated Theory Formation
2. More Sophisticated Mathematical Theory Formation
Models
3. The Combination of Reasoning Systems
4. Applications to Discovery Tasks in Pure
Mathematics
5. Applications of ATF and Combined Reasoning to Other
Domains
6. Improvement of AI Techniques
7. Automating Graphic Design and Visual Arts Processes
8. Issues in Automated Game Design
9. Automating Tasks in Creative Language
10. Addressing Questions of Computational Creativity
Research Collaborators
I am an Artificial Intelligence (AI) researcher. I aim to stretch the
boundaries of the intelligent tasks that computers can undertake
successfully. I am particularly interested in questions of
computational creativity, where the aim is to enable software to take
on creative responsibility in scientific and artistic projects. I
co-lead the Computational Creativity Group at Goldsmiths and the
MetaMakers Institute at Falmouth, and much of the research described
here has been undertaken in conjunction with group members, in
addition to colleagues from various Universities and companies in the
UK and around the world. For more details of research undertaken in
the computational creativity group, please visit the webpages here:
ccg.doc.gold.ac.uk. For
more details of the research undertaken in the MetaMakers Institute,
please visit the web pages here:
www.metamakersinstitute.com.
The AI research that I've been involved in fits largely into the
subfield of Computational Creativity. I am well known for the
development of creative systems such as the HR automated theory
formation system, The Painting Fool automated artist, the WhatIf
Machine fictional ideation system and the Wevva videogame
design app. I've applied such systems in various application domains,
including pure mathematics, formal modelling, graphic design, the
visual arts, creative language and videogame design. Building on
numerous experimental, practical and outreach projects with these
systems, I've also proposed a number of formalisms for the assessment
of progress towards creative software, and written about philosophical
issues surrounding the idea of software being creative. My research
can be broadly categorised into the ten areas described below.
Automated Theory Formation (ATF) is a novel hybrid machine
learning/automated reasoning technique which has been developed over
20 years, and which is implemented in the HR system. Given some
background knowledge, HR forms new concepts from old ones using a set
of production rules, and then makes conjectures which relate the
concepts, by appealing to empirical patterns in the examples of the
concepts. HR then uses third party systems to prove/disprove the
conjectures. HR also interacts with computer algebra systems such as
Maple and Gap, in order to calculate values for concepts. To drive a
heuristic search, HR uses a weighted sum - with the weights set by the
user - of measures of interestingness for concepts, i.e., having
decided which concept is most interesting, HR builds new concepts from
this. I've recently re-imagined and re-engineered HR as an automated
programming system. My book is the main reference text for Automated
Theory Formation.
The following papers describe some of the fundamental aspects of
automated theory formation (ATF). The first paper is the most recent
reference about the latest incarnation of the HR system. The second
paper is the main reference for ATF as an Inductive Logic Programming
system, the other papers are from quite early on in the development of
ATF.
We have taken Automated Theory Formation as the basis for more
in-depth studies into how mathematical theories can be formed
automatically. In addition to providing extensions to the basic
automated theory formation model and providing more background to the
subject, these projects have led to more sophisticated systems for
mathematical invention and machine learning in general, which take
into account philosophical and psychological perspectives on theory
formation. The following papers describe some of our projects in this
area:
As described above, the HR system for theory formation routinely
appeals to third party software as part of its core routine. This led
us to address the more general question of when it is possible to
combine AI techniques so that the whole is more than a sum of the
parts. In total, we have experimented with various combinations of
around 20 different AI systems, including descriptive and predictive
machine learning systems, model generators, constraint solvers,
satisfiability solvers, theorem provers and computer algebra
systems. Many of the applications described below make use of a
combination of reasoning systems. We have also looked at some more
generic ways to combine AI systems. The following papers describe some
of our projects in this area:
Pure mathematics is a unique domain for AI research, as mathematical
enquiry involves many diverse forms of reasoning, hence we can look at
the question of theory formation in pure mathematics and study
computational systems which combine different AI techniques. In
addition, the data in pure mathematics is usually error free, hence we
can concentrate on pure forms of reasoning without (usually) requiring
statistical interpretations. On numerous occasions, we have shown that
HR and other systems can make mathematical discoveries of genuine
value in graph theory, number theory and various algebraic domains of
pure mathematics. In addition, by combining HR with multiple other AI
systems, we have achieved new partial classifications of algebraic
domains, which were previously beyond any computational system or
human endeavour. The following papers describe some of our projects in
this area:
While pure mathematics has many advantages, other application domains
also stretch the limits of AI systems and their combinations. In order
to address the generic nature of the AI systems we have built, we have
looked at various non-mathematical applications of ATF. In addition to
the projects below, through the supervision of masters projects, we
have looked at the usage of HR for musical anomaly detection, for
discovery tasks in the gene ontology, for the analysis of board games
and the invention of arithmetic puzzles, and for the discovery of
software invariants. The following papers describe some of our
projects in this area:
Given that our overall research goal is to improve the application of
AI systems to intelligent tasks, it was sensible for us to question
whether combined reasoning systems can improve upon stand-alone
systems at standard tasks. Through our experiments with combined
reasoning systems, we have shown in many cases that (a) combined
reasoning systems can be more flexible in application than stand alone
systems (b) combined reasoning systems can be more effective at
solving traditional problems than stand alone systems, and (c)
combined reasoning systems can undertake intelligent tasks that no
single system can attempt. The following papers describe some of our
projects in this area:
While the HR system provided a good platform for the study of how to
automate mathematical and scientific creative processes, in order to
further study computational creativity, we have also undertaken a
number of projects aimed at automating processes in the creative
industries. In particular, we have built The Painting Fool
(www.thepaintingfool.com)
as a software artist, which we hope will be taken seriously as a
creative artist in its own right, one day. In order to facilitate the
creative construction of scenes, we have pushed evolutionary and
constraint solving techniques to the limit. We have also looked into
various evolutionary art projects, and we have introduced a new
browsing paradigm called Objet Trouve Computing, where the software
drives the process as much as the user, but also learns the user's
preferences along the way. The following papers describe some of our
projects in this area:
We have been working with video games companies towards the long term
goal of dynamically adapting games, which tailor their content and
gameplay to individual players, by learning about them and predicting
how their experience will change as the game changes. We have
concentrated on evaluating and predicting player experience from their
gameplay data, in addition to working on content generation projects
and the use of Monte-Carlo Tree Search methods. Through the ANGELINA
system, we have also studied how entire games can be generated through
a co-evolution procedure, which has brought up a number of
higher-level issues such as player verbs, subjectivity, software as
part of a creative community and automated code generation. We have
looked at various aspects of procedural content generation, and at how
AI methods can support the design process for fluidic games
which are meant to be changed by each different user, and possibly
passed on. The following papers describe some of our projects in this area:
Our newest application domain is creative language, where we have
looked at poetry generation as part of The Painting Fool project, and
we have built The What-If Machine for fictional ideation. One of our
main contributions is to push the idea of software accounting for its
actions via generating texts which acts as commentaries on what it has
done, why, and what it has produced. The following papers describe some of
our projects in this area:
Computational Creativity is the subfield of AI research where we try
to hand over creative responsibility to software, so that unbiased
observers would deem the software to be creative. Investigating the
affordances of creative software, its limitations and its impact on
certain stakeholder groups has led us to write about various
philosophical implications and issues, such as framing, Turing-style
tests and subjectivity. We have introduced/extended notions such as
the humanity gap, the latent heat effect, and creativity as an
essentially contested concept. We have also derived a number of
formalisms for different stakeholder groups which enable people to
assess progress of software towards being taken seriously as being
creative. The following papers describe some of our projects in this
area:
I've been very fortunate to work with a number of excellent
researchers, including the following co-authors (in surname
alphabetical order):
Overview
1. The Development of Automated Theory Formation
2. More Sophisticated Mathematical Theory Formation Models
3. The Combination of Reasoning Systems
4. Applications to Discovery Tasks in Pure Mathematics
5. Applications of ATF and Combined Reasoning to Other Domains
6. Improvement of AI Techniques
7. Automating Graphic Design and Visual Arts Processes
8. Issues in Automated Game Design
9. Automating Tasks in Creative Language
10. Addressing Questions of Computational Creativity
Research Collaborators
|
|
|
|