Meta learning evolutionary artificial neural networks
By Ajith Abraham. 2004
199 citations recorded by the source corpus.
Abstract In this paper, we present meta-learning evolutionary artificial neural network (MLEANN), an automatic computational framework for the adaptive optimization of artificial neural networks (ANNs) wherein the neural network architecture, activation function, connection weights; learning algorithm and its parameters are adapted according to the problem. We explored the performance of MLEANN and conventionally designed ANNs for function approximation problems. To evaluate the comparative performance, we used three different well-known chaotic time series. We also present the state-of-the-art popular neural network learning algorithms and some experimentation results related to convergence speed and generalization performance. We explored the performance of backpropagation algorithm; conjugate gradient algorithm, quasi-Newton algorithm and Levenberg–Marquardt algorithm for the three chaotic time series. Performances of the different learning algorithms were evaluated when the activation functions and architecture were changed. We further present the theoretical background, algorithm, design strategy and further demonstrate how effective and inevitable is the proposed MLEANN framework to design a neural network, which is smaller, faster and with a better generalization performance.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sebastian Risi
- Andrea Soltoggio
- Kenneth O. Stanley
- Jeff Clune
- Ajith Abraham
- Václav Snásel
- Varun Ojha
- Joel Lehman
Citations in the corpus
- Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “Abraham (2004) proposed a method called Meta-Learning Evolutionary Artificial Neural Networks (MLEANN) in which evolution searches for initial weights, neural architectures and transfer functions, and finally optimizes existing learning rules.”
- Global optimization issues in deep network regression: an overview (2018, unknown): “[1,103]) which is not theoretically justified.”
- Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, background): “Figure 6: Meta-learning scheme (a), where LR is learning parameter, ND is activation function, AR is architecture, and WT is weight [256].”