Autonomous Experimentation:Active Learning for Enzyme Response Characterisation

Cliff Lovell, Gareth Jones, Steve R. Gunn, Klaus-Peter Zauner
Active Learning and Experimental Design workshop In conjunction with AISTATS 2010, PMLR 16:141-155, 2011.

Abstract

Characterising response behaviours of biological systems is impaired by limited resources that restrict the exploration of high dimensional parameter spaces. Additionally, experimental errors that provide observations not representative of the true underlying behaviour, mean that observations obtained from these experiments cannot be regarded as always valid. To combat the problem of erroneous observations in situations where there are limited observations available to learn from, we consider the use of multiple hypotheses, where potentially erroneous observations are considered as being erroneous and valid in parallel by competing hypotheses. Here we describe work towards an autonomous experimentation machine that combines active learning techniques with computer controlled experimentation platforms to perform physical experiments. Whilst the target for our approach is the characterisation of the behaviours of networks of enzymes for novel computing mechanisms, the algorithms we are working towards remain independent of the application domain.

Cite this Paper

BibTeX
@InProceedings{pmlr-v16-lovel11a, title = {Autonomous Experimentation:Active Learning for Enzyme Response Characterisation}, author = {Lovell, Cliff and Jones, Gareth and Gunn, Steve R. and Zauner, Klaus-Peter}, booktitle = {Active Learning and Experimental Design workshop In conjunction with AISTATS 2010}, pages = {141--155}, year = {2011}, editor = {Guyon, Isabelle and Cawley, Gavin and Dror, Gideon and Lemaire, Vincent and Statnikov, Alexander}, volume = {16}, series = {Proceedings of Machine Learning Research}, address = {Sardinia, Italy}, month = {16 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v16/lovel11a/lovel11a.pdf}, url = {https://proceedings.mlr.press/v16/lovel11a.html}, abstract = {Characterising response behaviours of biological systems is impaired by limited resources that restrict the exploration of high dimensional parameter spaces. Additionally, experimental errors that provide observations not representative of the true underlying behaviour, mean that observations obtained from these experiments cannot be regarded as always valid. To combat the problem of erroneous observations in situations where there are limited observations available to learn from, we consider the use of multiple hypotheses, where potentially erroneous observations are considered as being erroneous and valid in parallel by competing hypotheses. Here we describe work towards an autonomous experimentation machine that combines active learning techniques with computer controlled experimentation platforms to perform physical experiments. Whilst the target for our approach is the characterisation of the behaviours of networks of enzymes for novel computing mechanisms, the algorithms we are working towards remain independent of the application domain.} }
Endnote
%0 Conference Paper %T Autonomous Experimentation:Active Learning for Enzyme Response Characterisation %A Cliff Lovell %A Gareth Jones %A Steve R. Gunn %A Klaus-Peter Zauner %B Active Learning and Experimental Design workshop In conjunction with AISTATS 2010 %C Proceedings of Machine Learning Research %D 2011 %E Isabelle Guyon %E Gavin Cawley %E Gideon Dror %E Vincent Lemaire %E Alexander Statnikov %F pmlr-v16-lovel11a %I PMLR %P 141--155 %U https://proceedings.mlr.press/v16/lovel11a.html %V 16 %X Characterising response behaviours of biological systems is impaired by limited resources that restrict the exploration of high dimensional parameter spaces. Additionally, experimental errors that provide observations not representative of the true underlying behaviour, mean that observations obtained from these experiments cannot be regarded as always valid. To combat the problem of erroneous observations in situations where there are limited observations available to learn from, we consider the use of multiple hypotheses, where potentially erroneous observations are considered as being erroneous and valid in parallel by competing hypotheses. Here we describe work towards an autonomous experimentation machine that combines active learning techniques with computer controlled experimentation platforms to perform physical experiments. Whilst the target for our approach is the characterisation of the behaviours of networks of enzymes for novel computing mechanisms, the algorithms we are working towards remain independent of the application domain.
RIS
TY - CPAPER TI - Autonomous Experimentation:Active Learning for Enzyme Response Characterisation AU - Cliff Lovell AU - Gareth Jones AU - Steve R. Gunn AU - Klaus-Peter Zauner BT - Active Learning and Experimental Design workshop In conjunction with AISTATS 2010 DA - 2011/04/21 ED - Isabelle Guyon ED - Gavin Cawley ED - Gideon Dror ED - Vincent Lemaire ED - Alexander Statnikov ID - pmlr-v16-lovel11a PB - PMLR DP - Proceedings of Machine Learning Research VL - 16 SP - 141 EP - 155 L1 - http://proceedings.mlr.press/v16/lovel11a/lovel11a.pdf UR - https://proceedings.mlr.press/v16/lovel11a.html AB - Characterising response behaviours of biological systems is impaired by limited resources that restrict the exploration of high dimensional parameter spaces. Additionally, experimental errors that provide observations not representative of the true underlying behaviour, mean that observations obtained from these experiments cannot be regarded as always valid. To combat the problem of erroneous observations in situations where there are limited observations available to learn from, we consider the use of multiple hypotheses, where potentially erroneous observations are considered as being erroneous and valid in parallel by competing hypotheses. Here we describe work towards an autonomous experimentation machine that combines active learning techniques with computer controlled experimentation platforms to perform physical experiments. Whilst the target for our approach is the characterisation of the behaviours of networks of enzymes for novel computing mechanisms, the algorithms we are working towards remain independent of the application domain. ER -
APA
Lovell, C., Jones, G., Gunn, S.R. & Zauner, K.. (2011). Autonomous Experimentation:Active Learning for Enzyme Response Characterisation. Active Learning and Experimental Design workshop In conjunction with AISTATS 2010, in Proceedings of Machine Learning Research 16:141-155 Available from https://proceedings.mlr.press/v16/lovel11a.html.

Related Material