A New Initialization Algorithm for Bees Algorithm

2013 ◽  
pp. 39-52 ◽  
Author(s):  
Wasim A. Hussein ◽  
Shahnorbanun Sahran ◽  
Siti Norul Huda Sheikh Abdullah
Keyword(s):  
Bees Algorithm ◽  
Initialization Algorithm

Patch-Levy-based initialization algorithm for Bees Algorithm

2014 ◽  
Vol 23 ◽  
pp. 104-121 ◽  
Author(s):  
Wasim A. Hussein ◽  
Shahnorbanun Sahran ◽  
Siti Norul Huda Sheikh Abdullah
Keyword(s):  
Bees Algorithm ◽  
Initialization Algorithm

Fuzzy logic, neural-fuzzy network and honey bees algorithm to develop the swarm motion of aerial robots

2021 ◽  
Author(s):  
Iman Shafieenejad ◽  
Elham Dehghan Rouzi ◽  
Jamshid Sardari ◽  
Mohammad Siami Araghi ◽  
Amirhosein Esmaeili ◽  
...  
Keyword(s):  
Fuzzy Logic ◽  
Honey Bees ◽  
Bees Algorithm ◽  
Aerial Robots ◽  
Fuzzy Network ◽  
Neural Fuzzy Network ◽  
Neural Fuzzy

Engineering Problem Optimized Using Bees Algorithm

2019 ◽  
pp. 99-105
Author(s):  
Kaushik Kumar ◽  
Divya Zindani ◽  
J. Paulo Davim
Keyword(s):  
Engineering Problem ◽  
Bees Algorithm

Analyzing and Accelerating the Bottlenecks of Training Deep SNNs With Backpropagation

2020 ◽  
Vol 32 (12) ◽  
pp. 2557-2600
Author(s):  
Ruizhi Chen ◽  
Ling Li
Keyword(s):  
Neural Networks ◽  
Training Algorithms ◽  
Minimization Method ◽  
Data Set ◽  
Ultra Low Power ◽  
Training Performance ◽  
Speed Up ◽  
Pros And Cons ◽  
Accuracy Increase ◽  
Initialization Algorithm

Spiking neural networks (SNNs) with the event-driven manner of transmitting spikes consume ultra-low power on neuromorphic chips. However, training deep SNNs is still challenging compared to convolutional neural networks (CNNs). The SNN training algorithms have not achieved the same performance as CNNs. In this letter, we aim to understand the intrinsic limitations of SNN training to design better algorithms. First, the pros and cons of typical SNN training algorithms are analyzed. Then it is found that the spatiotemporal backpropagation algorithm (STBP) has potential in training deep SNNs due to its simplicity and fast convergence. Later, the main bottlenecks of the STBP algorithm are analyzed, and three conditions for training deep SNNs with the STBP algorithm are derived. By analyzing the connection between CNNs and SNNs, we propose a weight initialization algorithm to satisfy the three conditions. Moreover, we propose an error minimization method and a modified loss function to further improve the training performance. Experimental results show that the proposed method achieves 91.53% accuracy on the CIFAR10 data set with 1% accuracy increase over the STBP algorithm and decreases the training epochs on the MNIST data set to 15 epochs (over 13 times speed-up compared to the STBP algorithm). The proposed method also decreases classification latency by over 25 times compared to the CNN-SNN conversion algorithms. In addition, the proposed method works robustly for very deep SNNs, while the STBP algorithm fails in a 19-layer SNN.

scholarly journals A Hybrid SFL-Bees Algorithm

2015 ◽  
Vol 128 (5) ◽  
pp. 13-18
Author(s):  
Duc Hoang
Keyword(s):  
Bees Algorithm

scholarly journals Bees Algorithm for multimodal function optimisation

2015 ◽  
Vol 230 (5) ◽  
pp. 867-884 ◽  
Author(s):  
ZD Zhou ◽  
YQ Xie ◽  
DT Pham ◽  
S Kamsani ◽  
M Castellani
Keyword(s):  
Global Optimum ◽  
Bees Algorithm ◽  
Benchmark Problems ◽  
Search Technique ◽  
Local Optima ◽  
Multimodal Function ◽  
Real World Applications ◽  
Speed Up ◽  
Search Approach ◽  
Optimisation Procedure

The aim of multimodal optimisation is to find significant optima of a multimodal objective function including its global optimum. Many real-world applications are multimodal optimisation problems requiring multiple optimal solutions. The Bees Algorithm is a global optimisation procedure inspired by the foraging behaviour of honeybees. In this paper, several procedures are introduced to enhance the algorithm’s capability to find multiple optima in multimodal optimisation problems. In the proposed Bees Algorithm for multimodal optimisation, dynamic colony size is permitted to automatically adapt the search effort to different objective functions. A local search approach called balanced search technique is also proposed to speed up the algorithm. In addition, two procedures of radius estimation and optima elitism are added, to respectively enhance the Bees Algorithm’s ability to locate unevenly distributed optima, and eliminate insignificant local optima. The performance of the modified Bees Algorithm is evaluated on well-known benchmark problems, and the results are compared with those obtained by several other state-of-the-art algorithms. The results indicate that the proposed algorithm inherits excellent properties from the standard Bees Algorithm, obtaining notable efficiency for solving multimodal optimisation problems due to the introduced modifications.

Sign in / Sign up

Export Citation Format

Share Document