Data classification using logarithmic spiral method based on RBF classifiers

Guerfala, Mohamed Wajih; Sifaoui, Amel; Abdelkrim, Afef

doi:10.1109/setit.2016.7939906

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though GSS has been primarily developed to find the extremum (minimum or maximum) for a univariate and unimodal function over a closed interval, it could also be applied in multi-dimensional cases with certain limitations. Similarly, efficient ML algorithms for data classification tasks have been developed using spiral golden angle which is parametrized by radius(r), angle (θ), φ and Golden Angle(ψ) [8], [9]. Luwes [10] has investigated the performance of neural network with weight matrix that has been initialized according to the Fibonacci sequence and has compared the results with randomly initialized weight matrix.…”

Section: Introductionmentioning

confidence: 99%

Investigation of weight initialization using Fibonacci Sequence on the performance of neural networks*

Mukherjee¹,

Yeri²

2021

Preprint

View full text Add to dashboard Cite

<div>Initializing weights are important for fast convergence and performance improvement of Artificial Neural Network models. This study proposes a heuristic method to initialize weights for Neural Network with Fibonacci sequence. Experiments have been carried out with different network structures and datasets and results have been compared with other initialization techniques such as Zero, Random, Xavier and He. It has been observed that for small sized datasets, Fibonacci initialization technique reports 94% of test accuracy which is better than Random (85%) and close to Xavier (93%) and He (96%) initialization methods. Also, for medium sized dataset, we have noted that performance of Fibonacci weight initialization method is comparable with the same for Random, Xavier and He initialization techniques.</div>

show abstract

Section: Introductionmentioning

confidence: 99%