Metaheuristic design of feedforward neural networks: A review of two decades of research

By Varun Ojha, Ajith Abraham, Václav Snásel. 2017

548 citations recorded by the source corpus.

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

1. Andrés Camero
2. Enrique Alba
3. Jamal Toutouh
4. Thomas Bäck
5. Javier Ferrer
6. Zwe-Lee Gaing
7. Jun Zhang
8. Zhi-hui Zhan

In Computer Vision and Pattern Recognition

1. Andrés Camero
2. Enrique Alba
3. Jamal Toutouh
4. Thomas Bäck
5. Javier Ferrer

Citations in the corpus

• Bayesian Neural Architecture Search using A Training-Free Performance Metric (2020, methodology): “, grid search, evolutionary algorithms or Bayesian optimization [31].”
• Random error sampling-based recurrent neural network architecture optimization (2019, methodology): “However, in spite of this definition, it is rather common to arbitrarily define the architecture and then applied a learning rule (e.g., SGD) to optimize the set of weights [9].”
• A Specialized Evolutionary Strategy Using Mean Absolute Error Random Sampling to Design Recurrent Neural Networks (2019, background): “Meta-heuristics are well known optimization algorithms to address complex, non-linear, and non-differentiable problems [20], [9].”
• Waste generation prediction under uncertainty in smart cities through deep neuroevolution (2019, background): “RNNs are top-notch at predicting time series, however as all Deep Learning (DL) techniques the selection of an appropriate network design is a tough task [5].”
• DLOPT: Deep Learning Optimization Library (2018, background): “However, these solutions are not appropriate in a DL context due to the high complexity of DNNs 10 .”