Application of Genetic Algorithms to the Construction of Topologies for Multilayer Perceptrons

Schiffmann, Wolfram; Joost, Merten; Werner, Randolf

doi:10.1007/978-3-7091-7533-0_98

Cited by 53 publications

(29 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is not the purpose of the present paper to give an extensive description of any of them, and more information on these algorithms may be found in the references [18][19]. A comparison of the results obtained using the well known backpropagation and the resilientpropagation algorithms is given in the result part.…”

Section: Learning Functionmentioning

confidence: 95%

“…A comparison of the results obtained using the well known backpropagation and the resilientpropagation algorithms is given in the result part. For more details on this algorithm as well as on the backpropmomentum or the backpercolation algorithms, also presented as comparison in this study, the reader may consult references [17][18][19].…”

Section: Learning Functionmentioning

confidence: 99%

See 1 more Smart Citation

Neural networks for kinetic parameters determination, signal filtering and deconvolution in thermal analysis

Sbirrazzuoli

Brunel

Elegant

1997

Journal of Thermal Analysis

View full text Add to dashboard Cite

Feedforward neural networks have been used for kinetic parameters determination and signal filtering in differential scanning calorimetry. The proper learning function was chosen and the network topology was optimized, using an empiric procedure. The learning process was achieved using simulated thermoanalytical curves. The resilient-propagation algorithm have led to the best minimization of the error computed over all the patterns. Relative errors on the thermodynamic and kinetic parameters were evaluated and compared to those obtained with the usual thermal analysis methods (single scan methods). The errors are much lower, especially in presence of noisy signals. Then, our program was adapted to simulate thermal effects with known thermodynamic and kinetic parameters, generated electrically, using a PC computer and an electronic interface on the serial port. These thermal effects have been generated by using an inconel thread.

show abstract

Section: Learning Functionmentioning

confidence: 95%

Section: Learning Functionmentioning

confidence: 99%

Neural networks for kinetic parameters determination, signal filtering and deconvolution in thermal analysis

Sbirrazzuoli

Brunel

Elegant

1997

Journal of Thermal Analysis

View full text Add to dashboard Cite

show abstract

“…This kind of approach, together with others which may be incorporated into future AMS versions, such as the use of evolutionary strategies [9][10][11] or genetic algorithms [12][13][14][15][16][17] for architecture design and optimisation, will further increase the chances of automating ANN integration at all levels and for every type of user.…”

Section: The Connectionist Db Modelmentioning

confidence: 99%

“…The research carried out has analysed the integration levels with general-purpose commercial connectionist 4-tool DBs (listed with letters A, B, C and D), six non-commercial ones (E to J) and 13 ANNs applied to different specific domains (K to W). Table 1 shows the degree of integration with DBs of these three groups of tools in the following regard:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Networks Manipulation Server: Research on the Integration of Databases and Artificial Neural Networks

Santos

Arcay

Dorado

et al. 2002

Neural Comput Applic

View full text Add to dashboard Cite

This paper proposes a new whole and distributed integration approach between Artificial Neural Networks (ANNs) and Databases (DBs) taking into account the different stages of the former's lifecycle (training, test and running). The integration architecture which has been developed consists of an ANN Manipulation Server (AMS) based on a clientserver approach, which improves the ANNs' manipulation and experimentation capabilities considerably, and also those of their training and test sets, together with their modular reuse among possibly remote applications. Moreover, the chances of integrating ANNs and DBs are analysed, proposing a new level of integration which improves the integration features considerably. This level has not been contemplated yet at full reach in any of the commercial or experimental tools analysed up to the present date. Finally, the application of the integration architecture which has been developed to the specific domain of Environmental Impact Assessments (EIAs) is studied. Thus, the versatility and efficacy of that architecture for developing ANNs is tested. The enormous complexity of the functioning of the patterns which rule the environment's behaviour, and the great number of variables involved, make it the ideal domain for experimenting on the application of ANNs together with DBs.

show abstract

Memristive Devices and Networks for Brain‐Inspired Computing

Zhang

et al. 2019

Physica Rapid Research Ltrs

View full text Add to dashboard Cite

As the era of big data approaches, conventional digital computers face increasing difficulties in performance and power efficiency due to their von Neumann architecture. As a result, there is recently a tremendous upsurge of investigations on brain-inspired neuromorphic hardware with high parallelism and improved efficiency. Memristors are considered as promising building blocks for the realization of artificial synapses and neurons and can therefore be utilized to construct hardware neural networks. Here, a review is provided on existing approaches for the implementation of artificial synapses and neurons based on memristive devices; and the respective advantages and disadvantages of these approaches are evaluated. This is followed by a discussion of hardware accelerators and neuromorphic computing systems that exploit the parallel, in-memory and analog characteristics of memristive crossbar arrays as well as the intrinsic dynamics of memristors. Finally, the outstanding challenges are addressed that have not yet been resolved in the present studies, and future advances are discussed that might be needed for building intelligent and energy efficient neuromorphic systems.

show abstract

Application of Genetic Algorithms to the Construction of Topologies for Multilayer Perceptrons

Cited by 53 publications

References 6 publications

Neural networks for kinetic parameters determination, signal filtering and deconvolution in thermal analysis

Neural networks for kinetic parameters determination, signal filtering and deconvolution in thermal analysis

Artificial Neural Networks Manipulation Server: Research on the Integration of Databases and Artificial Neural Networks

Memristive Devices and Networks for Brain‐Inspired Computing

Contact Info

Product

Resources

About