Grant GR/M56067
Closed Loop Machine
Learning
Duration of the Project: 16 March 1999 - 15 March 2002.
Aims
Machine Learning systems that produce human-comprehensible
hypotheses from data are being increasingly used for knowledge
discovery within both business and science. These systems are
typically open loop, with no direct link between the Machine Learning
system and the collection of data. This project tested the
alternative of Closed Loop Machine Learning in which the system
not only selects but also carries out these trials in the learning
domain.
Results
A summary of all of the results the project can be down-loaded from here:
postscript,
pdf.
Highlights of the results are given below:
ASE-Progol
We developed ASE-Progol
with the aim of partially automating some aspects of scientific
work. These aspects include the processes of forming hypotheses,
devising trials to discriminate between these competing hypotheses,
physically performing these trials and then using the results of these
trials to converge upon an accurate hypothesis. ASE-Progol is an
Active Learning system which uses Inductive Logic Programming to
construct hypothesised first-order theories and uses a CART-like
algorithm to select trials for eliminating ILP derived hypotheses.
Functional Genomics
In simulated yeast growth tests ASE-Progol was used to rediscover how
genes participate in the aromatic amino acid pathway of the yeast
Saccharomyces cerevisiae. The cost of the chemicals consumed in
converging upon a hypothesis with an accuracy of around 88% was
reduced by five orders of magnitude when trials were selected
by ASE-Progol rather than being sampled at random. While the naive
strategy of always choosing the cheapest trial from the set of
candidate trials led to lower cumulative costs than ASE-Progol, both
the naive strategy and the random strategy took significantly longer
to converge upon a final hypothesis than ASE-Progol. For example
to reach an accuracy of 80%, ASE-Progol required 4 days while
random sampling required 6 days and the naive strategy required 10
days.
Robotics
Following the completion of the Closed Loop Machine Learning project,
ASE-Progol was incorporated into The Robot Scientist (see Nature 427(6971):247-252, 2004).
The Robot Scientist performed the yeast growth tests in-vitro
rather than in-silico using a standard laboratory robot
designed for these sorts of liquid handling tasks, namely the
Beckman/Coulter Biomek 2000.
People
This page is maintained by Chris Bryant.
Last updated on 8 May 2007.