A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training

By Jing-Ru Zhang, Jun Zhang, Tat-Ming Lok, Michael R. Lyu. Applied Mathematics and Computation, 2007

701 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8152aab8016fd8a0b2cb7963f70726f8312e32b7

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. Seyedali Mirjalili
2. Andrew Lewis
3. Mengchu Zhou
4. Shangce Gao
5. Yirui Wang
6. Jiahai Wang
7. Jiujun Cheng
8. Sheng Yang

In Computer Vision and Pattern Recognition

1. Seyedali Mirjalili
2. Mengchu Zhou
3. Sheng Yang
4. Guoliang Fan
5. Jiawei Luo
6. Meng Ding
7. Jie Cai
8. Shulin Wang

Citations in the corpus

• Articulated and Generalized Gaussian Kernel Correlation for Human Pose Estimation (2016, methodology): “To cope with this problem, we incorporate Particle Swarm Optimization (PSO) with gradient-based search to balance the effectiveness and efficiency when exploring the high-dimensional parameter space [48]–[50].”
• Feature selection in machine learning: A new perspective (2018, methodology): “SVM, BP-NN, RBF-NN, K-means, Hierarchical clustering, Density based clustering and so on [60-65].”
• Global optimization issues in deep network regression: an overview (2018, methodology): “…for FNN: simulated annealing [4,91,115]; evolutionary algorithms [28,62,97,104]; genetic algorithms [51,82,122]; particle swarm optimization (PSO) [146]; dynamic tunneling in the weight space as in [117] or in [38] where the TRUST algorithm [10,37] is applied in connection with a BP gradient…”
• Dendritic Neuron Model With Effective Learning Algorithms for Classification, Approximation, and Prediction (2019, methodology): “PSO has been usually used to train neural networks [45], [65]–[68], especially MLP [54].”
• Let a biogeography-based optimizer train your Multi-Layer Perceptron (2014, methodology): “There are three methods for representing (encoding) the weights and biases: vector, matrix, and binary [80].”
• Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm (2012, methodology): “According to [10], there are three methods of encoding and representing the weights and biases of FNNs for every agent in evolutionary algorithms.”