Category: Genetic Programming and Evolvable Machines

Learning local linear Jacobians for flexible and adaptive robot arm control

Abstract  Successful planning and control of robots strongly depends on the quality of kinematic models, which define mappings between
configuration space (e.g. joint angles) and task space (e.g. Cartesian coordinates of the end effector). O…

Abstract  

Successful planning and control of robots strongly depends on the quality of kinematic models, which define mappings between
configuration space (e.g. joint angles) and task space (e.g. Cartesian coordinates of the end effector). Often these models
are predefined, in which case, for example, unforeseen bodily changes may result in unpredictable behavior. We are interested
in a learning approach that can adapt to such changes—be they due to motor or sensory failures, or also due to the flexible
extension of the robot body by, for example, the usage of tools. We focus on learning locally linear forward velocity kinematics
models by means of the neuro-evolution approach XCSF. The algorithm learns self-supervised, executing movements autonomously
by means of goal-babbling. It preserves actuator redundancies, which can be exploited during movement execution to fulfill
current task constraints. For detailed evaluation purposes, we study the performance of XCSF when learning to control an anthropomorphic
seven degrees of freedom arm in simulation. We show that XCSF can learn large forward velocity kinematic mappings autonomously
and rather independently of the task space representation provided. The resulting mapping is highly suitable to resolve redundancies
on the fly during inverse, goal-directed control.

  • Content Type Journal Article
  • Pages 1-21
  • DOI 10.1007/s10710-011-9147-0
  • Authors
    • Patrick O. Stalph, Computer Science, Cognitive Modeling, University of Tübingen, Sand 14, 72076 Tübingen, Germany
    • Martin V. Butz, Computer Science, Cognitive Modeling, University of Tübingen, Sand 14, 72076 Tübingen, Germany

A Markovianity based optimisation algorithm

Abstract  Several Estimation of Distribution Algorithms (EDAs) based on Markov networks have been recently proposed. The key idea behind
these EDAs was to factorise the joint probability distribution of solution variables in terms of cliques…

Abstract  

Several Estimation of Distribution Algorithms (EDAs) based on Markov networks have been recently proposed. The key idea behind
these EDAs was to factorise the joint probability distribution of solution variables in terms of cliques in the undirected
graph. As such, they made use of the global Markov property of the Markov network in one form or another. This paper presents
a Markov Network based EDA that is based on the use of the local Markov property, the Markovianity, and does not directly
model the joint distribution. We call it Markovianity based Optimisation Algorithm. The algorithm combines a novel method
for extracting the neighbourhood structure from the mutual information between the variables, with a Gibbs sampler method
to generate new points. We present an extensive empirical validation of the algorithm on problems with complex interactions,
comparing its performance with other EDAs that use higher order interactions. We extend the analysis to other functions with
discrete representation, where EDA results are scarce, comparing the algorithm with state of the art EDAs that use marginal
product factorisations.

  • Content Type Journal Article
  • Pages 1-37
  • DOI 10.1007/s10710-011-9149-y
  • Authors
    • Siddhartha Shakya, Business Modelling and Operational Transformation Practice, BT Innovate and Design, Adastral Park, Ipswich, UK
    • Roberto Santana, Universidad Politécnica de Madrid, Campus de Montegacedo sn., 28660 Boadilla del Monte, Madrid, Spain
    • Jose A. Lozano, Facultad de Informática, University of the Basque Country, Paseo Manuel de Lardizábal 1, 20018 San Sebastian, Spain

Software review: the ECJ toolkit

Software review: the ECJ toolkit
Content Type Journal ArticleCategory Software ReviewPages 1-3DOI 10.1007/s10710-011-9148-zAuthors
David R. White, School of Computing Science, University of Glasgow, Lilybank Gardens, Glasgow, G12 8QQ UK

Journ…

Software review: the ECJ toolkit

  • Content Type Journal Article
  • Category Software Review
  • Pages 1-3
  • DOI 10.1007/s10710-011-9148-z
  • Authors
    • David R. White, School of Computing Science, University of Glasgow, Lilybank Gardens, Glasgow, G12 8QQ UK

Paul Coates: Programming architecture

Paul Coates: Programming architecture
Content Type Journal ArticleCategory Book ReviewPages 463-464DOI 10.1007/s10710-011-9146-1Authors
Benachir Medjdoub, School of the Built Environment, University of Salford, Salford, UK

Journal Genetic Pro…

Paul Coates: Programming architecture

  • Content Type Journal Article
  • Category Book Review
  • Pages 463-464
  • DOI 10.1007/s10710-011-9146-1
  • Authors
    • Benachir Medjdoub, School of the Built Environment, University of Salford, Salford, UK

Trent McConaghy, P. Palmers, G. Peng, Michiel Steyaert, Georges Gielen: Variation-aware analog structural synthesis: a computational intelligence approach

Trent McConaghy, P. Palmers, G. Peng, Michiel Steyaert, Georges Gielen: Variation-aware analog structural synthesis: a computational intelligence approach
Content Type Journal ArticleCategory Book ReviewPages 461-462DOI 10.1007/s10710-011-9145-2Author…

Trent McConaghy, P. Palmers, G. Peng, Michiel Steyaert, Georges Gielen: Variation-aware analog structural synthesis: a computational intelligence approach

  • Content Type Journal Article
  • Category Book Review
  • Pages 461-462
  • DOI 10.1007/s10710-011-9145-2
  • Authors
    • John Rieffel, Union College, Schenectady, NY, USA

Multi-class pattern classification using single, multi-dimensional feature-space feature extraction evolved by multi-objective genetic programming and its application to network intrusion detection

Abstract  In this paper we investigate using multi-objective genetic programming to evolve a feature extraction stage for multiple-class
classifiers. We find mappings which transform the input space into a new, multi-dimensional decision spa…

Abstract  

In this paper we investigate using multi-objective genetic programming to evolve a feature extraction stage for multiple-class
classifiers. We find mappings which transform the input space into a new, multi-dimensional decision space to increase the
discrimination between all classes; the number of dimensions of this decision space is optimized as part of the evolutionary
process. A simple and fast multi-class classifier is then implemented in this multi-dimensional decision space. Mapping to
a single decision space has significant computational advantages compared to k-class-to-2-class decompositions; a key design requirement in this work has been the ability to incorporate changing priors
and/or costs associated with mislabeling without retraining. We have employed multi-objective optimization in a Pareto framework
incorporating solution complexity as an independent objective to be minimized in addition to the main objective of the misclassification
error. We thus give preference to simpler solutions which tend to generalize well on unseen data, in accordance with Occam’s
Razor. We obtain classification results on a series of benchmark problems which are essentially identical to previous, more
complex decomposition approaches. Our solutions are much simpler and computationally attractive as well as able to readily
incorporate changing priors/costs. In addition, we have also applied our approach to the KDD-99 intrusion detection dataset
and obtained results which are highly competitive with the KDD-99 Cup winner but with a significantly simpler classification
framework.

  • Content Type Journal Article
  • Pages 1-31
  • DOI 10.1007/s10710-011-9143-4
  • Authors
    • Khaled Badran, Vision and Information Engineering Research Group, Department of Electronic and Electrical Engineering, The University of Sheffield, Mappin Street, Sheffield, S1 3D UK
    • Peter Rockett, Vision and Information Engineering Research Group, Department of Electronic and Electrical Engineering, The University of Sheffield, Mappin Street, Sheffield, S1 3D UK

The evolution of higher-level biochemical reaction models

Abstract  Computational tools for analyzing biochemical phenomena are becoming increasingly important. Recently, high-level formal languages
for modeling and simulating biochemical reactions have been proposed. These languages make the forma…

Abstract  

Computational tools for analyzing biochemical phenomena are becoming increasingly important. Recently, high-level formal languages
for modeling and simulating biochemical reactions have been proposed. These languages make the formal modeling of complex
reactions accessible to domain specialists outside of theoretical computer science. This research explores the use of genetic
programming to automate the construction of models written in one such language. Given a description of desired time-course
data, the goal is for genetic programming to construct a model that might generate the data. The language investigated is
Kahramanoğullari’s and Cardelli’s Programming Interface for Modeling (PIM) language. The PIM syntax is defined in a grammar-guided
genetic programming system. All time series generated during simulations are described by statistical feature tests, and the
fitness evaluation compares feature proximity between the target and candidate solutions. PIM models of varying complexity
were used as target expressions for genetic programming, and were successfully reconstructed in all cases. This shows that
the compositional nature of PIM models is amenable to genetic program search.

  • Content Type Journal Article
  • Pages 1-29
  • DOI 10.1007/s10710-011-9144-3
  • Authors
    • Brian J. Ross, Department of Computer Science, Brock University, 500 Glenridge Ave., St. Catharines, ON L2S 3A1, Canada

GPLAB: software review

GPLAB: software review
Content Type Journal ArticleCategory software reviewPages 457-459DOI 10.1007/s10710-011-9142-5Authors
Indriyati Atmosukarto, University of Washington, Seattle, WA, USA

Journal Genetic Programming and Evolvable MachinesO…

GPLAB: software review

  • Content Type Journal Article
  • Category software review
  • Pages 457-459
  • DOI 10.1007/s10710-011-9142-5
  • Authors
    • Indriyati Atmosukarto, University of Washington, Seattle, WA, USA

Challenges of evolvable hardware: past, present and the path to a promising future

Abstract  Nature is phenomenal. The achievements in, for example, evolution are everywhere to be seen: complexity, resilience, inventive
solutions and beauty. Evolvable Hardware (EH) is a field of evolutionary computation (EC) that focuses o…

Abstract  

Nature is phenomenal. The achievements in, for example, evolution are everywhere to be seen: complexity, resilience, inventive
solutions and beauty. Evolvable Hardware (EH) is a field of evolutionary computation (EC) that focuses on the embodiment of
evolution in a physical media. If EH could achieve even a small step in natural evolution’s achievements, it would be a significant
step for hardware designers. Before the field of EH began, EC had already shown artificial evolution to be a highly competitive
problem solver. EH thus started off as a new and exciting field with much promise. It seemed only a matter of time before
researchers would find ways to convert such techniques into hardware problem solvers and further refine the techniques to
achieve systems that were competitive with or better than human designs. However, 15 years on—it appears that problems solved
by EH are only of the size and complexity of that achievable in EC 15 years ago and seldom compete with traditional designs.
A critical review of the field is presented. Whilst highlighting some of the successes, it also considers why the field is
far from reaching these goals. The paper further redefines the field and speculates where the field should go in the next
10 years.

  • Content Type Journal Article
  • Pages 183-215
  • DOI 10.1007/s10710-011-9141-6
  • Authors
    • Pauline C. Haddow, CRAB Lab, Department of Computer and Information Science, Norwegian University of Science and Technology, Trondheim, Norway
    • Andy M. Tyrrell, Intelligent Systems Group, Department of Electronics, University of York, York, UK

Long memory time series forecasting by using genetic programming

Abstract  Real-world time series have certain properties, such as stationarity, seasonality, linearity, among others, which determine
their underlying behaviour. There is a particular class of time series called long-memory processes, charac…

Abstract  

Real-world time series have certain properties, such as stationarity, seasonality, linearity, among others, which determine
their underlying behaviour. There is a particular class of time series called long-memory processes, characterized by a persistent
temporal dependence between distant observations, that is, the time series values depend not only on recent past values but
also on observations of much prior time periods. The main purpose of this research is the development, application, and evaluation
of a computational intelligence method specifically tailored for long memory time series forecasting, with emphasis on many-step-ahead
prediction. The method proposed here is a hybrid combining genetic programming and the fractionally integrated (long-memory)
component of autoregressive fractionally integrated moving average (ARFIMA) models. Another objective of this study is the
discovery of useful comprehensible novel knowledge, represented as time series predictive models. In this respect, a new evolutionary
multi-objective search method is proposed to limit complexity of evolved solutions and to improve predictive quality. Using
these methods allows for obtaining lower complexity (and possibly more comprehensible) models with high predictive quality,
keeping run time and memory requirements low, and avoiding bloat and over-fitting. The methods are assessed on five real-world
long memory time series and their performance is compared to that of statistical models reported in the literature. Experimental
results show the proposed methods’ advantages in long memory time series forecasting.

  • Content Type Journal Article
  • Pages 429-456
  • DOI 10.1007/s10710-011-9140-7
  • Authors
    • Emiliano Carreño Jara, Departamento de Informática, Universidad Nacional de San Luis, Ejército de los Andes 950, San Luis, D5700HHW Argentina