Information-based objective functions for active data selection
Neural Computation
Selective Sampling Using the Query by Committee Algorithm
Machine Learning
Query Learning Strategies Using Boosting and Bagging
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Employing EM and Pool-Based Active Learning for Text Classification
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Active learning with statistical models
Journal of Artificial Intelligence Research
Active learning for regression based on query by committee
IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Automated discovery in a chemistry laboratory
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
Identifying the characteristics of biological systems through physical experimentation, is restricted by the resources available, which are limited in comparison to the size of the parameter spaces being investigated. New tools are required to assist scientists in the effective characterisation of such behaviours. By combining artificial intelligence techniques for active experiment selection, with a microfluidic experimentation platform that reduces the volumes of reactants required per experiment, a fully autonomous experimentation machine is in development to assist biological response characterisation. Part of this machine, an artificial experimenter, has been designed that automatically proposes hypotheses, then determines experiments to test those hypotheses and explore the parameter space. Using a multiple hypotheses approach that allows for representative models of response behaviours to be produced with few observations, the artificial experimenter has been employed in a laboratory setting, where it selected experiments for a human scientist to perform, to investigate the optical absorbance properties of NADH.