Biomedical subjects

Larry Bull

Publications and source records attributed to Larry Bull.

5 recordsLinked to original sources

PubMed2007

Using the XCS classifier system for multi-objective reinforcement learning problems.

We investigate the performance of a learning classifier system in some simple multi-objective, multi-step maze problems, using both random and biased action-selection policies for exploration. Results show that the choice of action-selection policy can significantly affect the performance of the system in such environments. Further, this effect is directly related to population size, and we relate this finding to recent theoretical studies of learning classifier systems in single-step problems.

Artificial Intelligence↗

PubMed2006

Electrophysiological measurements in three-dimensional in vivo-mimetic organotypic cell cultures: preliminary studies with hen embryo brain spheroids.

Using three-dimensional artificial tissue constructs shown to offer organotypic functionality, hen embryo brain spheroids were used as a novel electrophysiological paradigm. For the first time, single spontaneous action potentials were recorded from spheroids in culture at day 7 in vitro (DIV) using multi-electrode arrays. At DIV14 'bursting behaviour' was observed. Simple stimulation was found to induce an increase in spiking frequency with an effect that ramped up over DIV7-14. By DIV14, the frequency under stimulation was typically over twice that of the corresponding spontaneous spiking. These results indicate strong self-organizing processes in vitro within the neuronal networks of the three-dimensional spheroid cell cultures. The organotypic in vivo-mimetic nature of the spheroid paradigm was confirmed by electron microscopy that revealed an outer layer of glial cells, a glial limitans, while immunostaining for Neurofilament and Glial Fibrilliary Acidic Protein demonstrated neuronal cells with a centralized neuronal and synaptic distribution. Basic biochemical functionality was also determined and Acetylcholinesterase measured, indicating the activity of acetylcholine receptors. Thus the organotypic hen embryo brain spheroid model may offer a new paradigm in which to explore neuronal networks.

Animals↗

PubMed2006

A neural learning classifier system with self-adaptive constructivism for mobile robot control.

For artificial entities to achieve true autonomy and display complex lifelike behavior, they will need to exploit appropriate adaptable learning algorithms. In this context adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn appropriate behaviors. This article examines the use of constructivism-inspired mechanisms within a neural learning classifier system architecture that exploits parameter self-adaptation as an approach to realize such behavior. The system uses a rule structure in which each rule is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task. Results are presented in simulated mazes before moving to a mobile robot platform.

Algorithms↗

PubMed2003

For real! XCS with continuous-valued inputs.

Many real-world problems are not conveniently expressed using the ternary representation typically used by Learning Classifier Systems and for such problems an interval-based representation is preferable. We analyse two interval-based representations recently proposed for XCS, together with their associated operators and find evidence of considerable representational and operator bias. We propose a new interval-based representation that is more straightforward than the previous ones and analyse its bias. The representations presented and their analysis are also applicable to other Learning Classifier System architectures. We discuss limitations of the real multiplexer problem, a benchmark problem used for Learning Classifier Systems that have a continuous-valued representation, and propose a new test problem, the checkerboard problem, that matches many classes of real-world problem more closely than the real multiplexer. Representations and operators are compared using both the real multiplexer and checkerboard problems and we find that representational, operator and sampling bias all affect the performance of XCS in continuous-valued environments.

Classification↗

PubMed2002

ZCS redux.

Learning classifier systems traditionally use genetic algorithms to facilitate rule discovery, where rule fitness is payoff based. Current research has shifted to the use of accuracy-based fitness. This paper re-examines the use of a particular payoff-based learning classifier system--ZCS. By using simple difference equation models of ZCS, we show that this system is capable of optimal performance subject to appropriate parameter settings. This is demonstrated for both single- and multistep tasks. Optimal performance of ZCS in well-known, multistep maze tasks is then presented to support the findings from the models.

Algorithms↗