| Home  | About ScienceAsia  | Publication charge  | Subscription for printed version  | Contact us  
Editorial Board
Journal Policy
Instructions for Authors
Online submission
Author Login
Reviewer Login
Volume 46 Number 5
Volume 46 Number 4
Volume 46 Number 3
Volume 46 Number 2
Volume 46 Number 1
Volume 46S Number 1
Earlier issues
Supplement issue

About "Bio Inspired and Natural Inspired Analysis of Deep Learning Algorithms"
Neural information processing is an emerging field with significant importance that greatly influence the modern world. It is an interdisciplinary science that involves neural networks and artificial intelligence techniques. Deep learning is an important application of neural information processing systems that enables easier classification of unstructured data with unsupervised learning models. It allows a model to work on its own to discover information, extract features, and perform classification most effectively. Most of the deep learning models work based on the Convolutional Neural Networks (CNN) with multiple layers. Bio-Inspired analysis for deep learning has gained significant consideration from researchers of various backgrounds due to the reason that bio-inspired analysis provides self-learning, adaptive, and most efficient solutions. These algorithms are computationally fast in nature with lesser sensitivity to input parameters. For the past few decades, numerous biologically inspired algorithms have been developed such as particle swarm optimization, ant colony optimization, metaheuristic algorithms, genetic algorithms, and many more. Appropriate use of these techniques across deep learning systems forms the basis of next-generation intelligence optimization algorithms.

In general, bio-inspired algorithms provide optimal solutions for specific problems. These algorithms solve different optimization problems in computer science using observations from naturally inspired insects and animals. The biological behaviour of the animals is interpreted into mathematical modules and initial parameters through which the algorithms are defined and tested. Depending upon the input and output parameters, the performance of the algorithm is evaluated. Many of these algorithms are built using biologically inspired actions such as food searching, natural collection, group movements, and several other natural activities acts as an effective alternative for traditional optimization techniques. On the other hand, the use of these algorithms with advanced techniques such as deep learning can provide excellent performance and optimization measures to practical real-world applications such as big data analysis, Internet of Things (IoT), Cyber-Physical Systems (CPS), Cyber Security, etc. However, solving complicated problems with high dimensions and increased uncertainty remains to be an open challenge for researchers and scholars who work in the field of Intelligence computing. This special issue is specifically formulated with the intent to motivate researchers from various fields to present the novel and optimal solution for deep learning using bio-inspired analysis. The topics of the special issue include but not limited to the following:

  • Nature-inspired optimization algorithms for deep learning
  • Advancement in bio-inspired computational intelligence using deep learning
  • Application of bio-inspired computational intelligence algorithms for real-time systems (Internet of Things (IoT), Cyber-Physical System (CPS), etc.)
  • Challenges ahead for bio-inspired analysis for deep learning and its solution
  • Bio-inspired Computing-Its scope and applications
  • Key role of bio-inspired algorithms in performance optimization for deep learning
  • Bio-inspired computational intelligence: A new way of computing approach to real-time systems
  • New and novel biologically inspired algorithms for deep learning
  • Innovative approaches for feature selection and extraction in deep learning using bio-inspired algorithms
  • Object detection and computer vision using bio-inspired deep learning techniques
     SPECIAL ISSUE...........................................................................................................

Thematic Issue