Fast learning neural networks using Cartesian genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Khan:2013:Neurocomputing,

• author = "Maryam Mahsal Khan and Arbab Masood Ahmad and Gul Muhammad Khan and Julian F. Miller",
• title = "Fast learning neural networks using Cartesian genetic programming",
• journal = "Neurocomputing",
• year = "2013",
• volume = "121",
• pages = "274--289",
• month = "9 " # dec,
• keywords = "genetic algorithms, genetic programming, cartesian genetic programming, Artificial neural network, Pole balancing, Breast cancer, Neuroevolution, Recurrent networks",
• ISSN = "0925-2312",
• DOI = "doi:10.1016/j.neucom.2013.04.005",
• URL = "http://www.sciencedirect.com/science/article/pii/S0925231213004499",
• URL = "http://results.ref.ac.uk/Submissions/Output/3354639",
• abstract = "A fast learning neuroevolutionary algorithm for both feedforward and recurrent networks is proposed. The method is inspired by the well known and highly effective Cartesian genetic programming (CGP) technique. The proposed method is called the CGP-based Artificial Neural Network (CGPANN). The basic idea is to replace each computational node in CGP with an artificial neuron, thus producing an artificial neural network. The capabilities of CGPANN are tested in two diverse problem domains. Firstly, it has been tested on a standard benchmark control problem: single and double pole for both Markovian and non-Markovian cases. Results demonstrate that the method can generate effective neural architectures in substantially fewer evaluations in comparison to previously published neuroevolutionary techniques. In addition, the evolved networks show improved generalisation and robustness in comparison with other techniques. Secondly, we have explored the capabilities of CGPANNs for the diagnosis of Breast Cancer from the FNA (Finite Needle Aspiration) data samples. The results demonstrate that the proposed algorithm gives 99.5percent accurate results, thus making it an excellent choice for pattern recognitions in medical diagnosis, owing to its properties of fast learning and accuracy. The power of a CGP based ANN is its representation which leads to an efficient evolutionary search of suitable topologies. This opens new avenues for applying the proposed technique to other linear/non-linear and Markovian/non-Markovian control and pattern recognition problems.",
• uk_research_excellence_2014 = "This work advances the evolution of artificial neural networks. In collaboration with University of Engineering Technology in Peshawar, Pakistan, the work is the first journal publication on the evolution of artificial neural networks using Cartesian Genetic programming. Development of this work by a PhD student won best student paper at International Conference on Artificial Intelligence, Cambridge, 2013.",

}

Genetic Programming entries for Maryam Mahsal Khan Arbab Masood Ahmad Gul Muhammad Khan Julian F Miller

Citations