Salp Swarm Algorithm (SSA) for Training Feed-Forward Neural Networks

Bairathi, Divya; Gopalani, Dinesh

doi:10.1007/978-981-13-1592-3_41

Cited by 39 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last experiment, we compare our algorithm with 11 population-based trainers, namely particle swarm optimisation [11], artificial bee colony (ABC) [14], imperialist competitive algorithm (ICA) [15], firefly algorithm (FA) [18], grey wolf optimiser (GWO) [19], ant lion optimiser [21], dragonfly algorithm (DA) [22], sine cosine algorithm [23], whale optimisation algorithm (WOA) [24], grasshopper optimisation algorithm [25], and salp swarm algorithm (SSA) [56]. Algorithms such as PSO and ABC are among established training algorithms, while some others such as GOA and WOA are more recent.…”

Section: Resultsmentioning

confidence: 99%

Differential Evolution-based Neural Network Training Incorporating a Centroid-based Strategy and Dynamic Opposition-based Learning

Mousavirad¹,

Oliva²,

Hinojosa³

et al. 2021

Preprint

View full text Add to dashboard Cite

Training multi-layer neural networks (MLNNs), a challenging task, involves finding appropriate weights and biases. MLNN training is important since the performance of MLNNs is mainly dependent on these network parameters. However, conventional algorithms such as gradient-based methods, while extensively used for MLNN training, suffer from drawbacks such as a tendency to getting stuck in local optima. Population-based metaheuristic algorithms can be used to overcome these problems. In this paper, we propose a novel MLNN training algorithm, CenDE-DOBL, that is based on differential evolution (DE), a centroid-based strategy (Cen-S), and dynamic opposition-based learning (DOBL). The Cen-S approach employs the centroid of the best individuals as a member of population, while other members are updated using standard crossover and mutation operators. This improves exploitation since the new member is obtained based on the best individuals, while the employed DOBL strategy, which uses the opposite of an individual, leads to enhanced exploration. Our extensive experiments compare CenDE-DOBL to 26 conventional and population-based algorithms and confirm it to provide excellent MLNN training performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Differential Evolution-based Neural Network Training Incorporating a Centroid-based Strategy and Dynamic Opposition-based Learning

Mousavirad¹,

Oliva²,

Hinojosa³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the current year 2019 Bairathi et al castoff SSA algorithm with MLP network for obtaining optimal set of weights and biases. The efficiency was scrutinized by using standard datasets and by comparing with some recent metaheuristic algorithms [45]. In 2018 Haidari et al proposed MLP network with Grasshopper Optimization algorithm.…”

Section: A Background and Related Workmentioning

confidence: 99%

How Effective is Spotted Hyena Optimizer for Training Multilayer Perceptrons

Panda¹,

Majhi²

2019

IJRTE

View full text Add to dashboard Cite

This paper focuses on training multilayer perceptron (MLP) using a recently proposed meta-heuristic algorithm termed as Spotted Hyena Optimizer (SHO). To test the efficacy of the said algorithm fifteen standard datasets are used. At the same time the result of the proposed method is examined by some popular heuristic training algorithms such as Differential Evolution (DE), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Salp Swarm Algorithm (SSA) and Grey Wolf Optimization algorithm (GWO). Final result shows that SHO successfully avoids the local minima trap problem, simultaneously showing higher accuracy in classification as compared to other meta-heuristic methods. The statistical significance of the proposed SHO-MLP has been verified by deploying the Friedman & Holm’s test. It has been observed that the SHO-MLP is giving promisingly better result than other compared method for training MLP.

show abstract

“…It can be expressed as a disadvantage of deterministic approaches that adding extra hidden layers in the training of the network and being stuck in the local optimum depending on the first solution slows down the training of the network [33][34][35].Another technique used in training the network is stochastic algorithms [36]. Stochastic algorithms use randomness, which reduces the probability of getting stuck in the local minimum and makes it less dependent on the initial solution [37]. There are multiple types of stochastic algorithms, one of which is metaheuristic algorithms inspired by nature [38].…”

Section: Introductionmentioning

confidence: 99%

Website Phishing Technique Classification Detection with HSSJAYA Based MLP Training

2022

Teh. vjesn.

View full text Add to dashboard Cite

Website phishing technique is the process of stealing personal information (ID number, social media account information, credit card information etc.) of target users through fake websites that are similar to reality by users who do not have good intentions. There are multiple methods in detecting website phishing technique and one of them is multilayer perceptron (MLP), a type of artificial neural networks. The MLP occurs with at least three layers, the input, at least one hidden layer and the output. Data on the network must be trained by passing over neurons. There are multiple techniques in training the network, one of which is training with metaheuristic algorithms. Metaheuristic algorithms that aim to develop more effective hybrid algorithms by combining the good and successful aspects of more than one algorithm are algorithms inspired by nature. In this study, MLP was trained with Hybrid Salp Swarm Jaya (HSSJAYA) and used to determine whether websites are suspicious, phishing or legal. In order to compare the success of MLP trained with hybrid algorithm, Salp Swarm Algorithm (SSA) and Jaya (JAYA) were compared with MLPs trained with Cuckoo Algorithm (CS), Genetic Algorithm (GA) and Firefly Algorithm (FFA). As a result of the experimental and statistical analysis, it was determined that the MLP trained with HSSJAYA was successful in detecting the website phishing technique according to the results of other algorithms.

show abstract

Salp Swarm Algorithm (SSA) for Training Feed-Forward Neural Networks

Cited by 39 publications

References 14 publications

Differential Evolution-based Neural Network Training Incorporating a Centroid-based Strategy and Dynamic Opposition-based Learning

Differential Evolution-based Neural Network Training Incorporating a Centroid-based Strategy and Dynamic Opposition-based Learning

How Effective is Spotted Hyena Optimizer for Training Multilayer Perceptrons

Website Phishing Technique Classification Detection with HSSJAYA Based MLP Training

Contact Info

Product

Resources

About