Universiti Teknologi Malaysia Institutional Repository

Multi-strategy learning and deep harmony memory improvisation for self-organizing neurons

Hasan, Shafaatunnur and Shamsuddin, Siti Mariyam (2019) Multi-strategy learning and deep harmony memory improvisation for self-organizing neurons. Soft Computing, 23 (1). pp. 285-303. ISSN 1432-7643

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1007/s00500-018-3116-y


This study proposes a concept of representation learning by implementing multi-strategy deep learning harmony memory improvisation for selecting the best harmony of self-organizing neurons. Representation learning is a set of methods that allows a machine to be fed with raw data and to automatically discover the representations needed for detection or classification. In our study, the deep multi-strategy learning involves the convolution of the self-organizing neurons with deep harmony memories improvisation in self-organizing and representation of map learning. The convolution of self-organizing neurons and harmony memory optimize the representation neurons’ weights by generating the optimal best matching unit which is represented as fitness function of f1(x) and f2(x). While f1[g(f1′′(x))] and f2[g(f2′(x))] represent the New Harmony fitness function. The best fitness function, fbest(x) is selected based on the f1(x) and f2(x) performance which will be later stored in the harmony memory vector. The position vector of a particle is subjected to the Newtonian mechanics constant acceleration during the interval Δ t. The search space of self-organizing map with Newton-based particle swarm algorithm particles depends on the width area, σα(t) of organizing neurons lattice structure. Our proposed methods are experimented on various biomedical datasets. The findings indicate that the proposed methods provide better quantization error for clustering and good classification accuracy with statistical measurement validations.

Item Type:Article
Uncontrolled Keywords:deep learning, harmony search algorithm, machine learning
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
ID Code:87542
Deposited By: Yanti Mohd Shah
Deposited On:08 Nov 2020 12:06
Last Modified:08 Nov 2020 12:06

Repository Staff Only: item control page