Radial basis neural network optimization using fruit fly

Table of Contents

1. Introduction

1.1 Introduction

1.2 Motivation and Aim

1.3 Disposition

2. Artificial Neural Network

2.1 Biological Neuron

2.2 Artificial Neural Network

2.2.1 Single Layer Perceptron

2.2.2 Multi Layer Perceptron

2.3 Artificial Neuron and Activation Function

2.3.1 Linear Activation Function

2.3.2 Non Linear Activation Functions

2.3.3 Radial Basis Net

2.4 Learning Methods

2.4.1 Supervised Learning

2.4.2 Unsupervised learning

2.5 Neural Network Applications

2.5.1 Process Control

2.5.2 Speech Recognition

2.5.3 Image Compression

2.5.4 Medical Imaging

2.5.5 Image Processing

2.5.6 Face Recognition

2.5.7 Road and Obstacle Recognition

3. Neural Network Parallelism

3.1 General Aspects of Parallel Processing

3.2 Back Propagation Neural Network Parallelism

3.3 Neural Network Distribution

3.4 Distributed computing for BP parallelism

3.4.1 Training Set Parallelism

3.4.2 Node Parallelism

3.4.2.1 Neuron Parallelism

3.4.2.2 Synapse Parallelism

3.5 Need of Parallel Processing

4. Distributed Computing System

4.1 Distributed System

4.2 Distributed Computing System Models

4.2.1 Minicomputer Model

4.2.2 Workstation Model

4.2.3 Workstation-server Model

4.2.4 Processor Pool Model

4.2.5 Hybrid Model

4.3 Distributed Computing Environment

5. Fruit Fly

5.1 Fruit Fly

5.1.1 Fruit Fly Nervous System: Solution to Computer Problem

5.1.2 Fruit Fly takes Distributive Approach in Computing

5.2 Fruit Fly Revolutionize distributed computing

5.3 Fruit Fly Optimization

6. Literature Survey

6.1 Literature Review

7. Present Works

7.1 Overview

7.2 aFOA Algorithm

7.3 Radial Basis Neural Network

7.4 Variable Selection

7.5 Model Development

7.5.1 Data Preparation

7.5.2 Constructing Model

8. Framework and Technology

8.1 MATLAB

8.2 MemBrain

8.3 System and Models

8.3.1 System Requirement

8.3.2 MemBrain Mathematical Model

8.3.3 Learning algorithms

8.4 MemBrain DLL

8.5 Automatic Code Generation

9. Result and Discussion

9.1 Experimental results and analysis

9.2 Numerical Testing

9.3 Comparison

10. Conclusion

10.1 Conclusion

10.2 Challenge and Future Work

Research Objectives and Core Themes

This research aims to optimize the Radial Basis Function (RBF) neural network by utilizing the amended Fruit Fly Optimization Algorithm (aFOA) in combination with the Mean Impact Value (MIV) for effective variable selection to improve computational performance and modeling accuracy.

• Optimization of RBF neural networks using aFOA.
• Application of Mean Impact Value (MIV) for input variable screening.
• Parallel processing and distributed computing architectures for neural networks.
• Performance evaluation through experimental data and comparative analysis with existing optimization algorithms.

Excerpt from the Book

Summary of Chapters

Chapter 1 Introduction: Provides an overview of the thesis, outlining the motivation for using parallel-distributed neural networks and the objectives of the research.

Chapter 2 Artificial Neural Network: Details the fundamental concepts of biological neurons and various artificial neural network architectures, including single and multi-layer perceptrons.

Chapter 3 Neural Network Parallelism: Explains the necessity and implementation of parallel processing techniques for back-propagation in neural networks.

Chapter 4 Distributed Computing System: Discusses various models of distributed computing, ranging from workstation models to processor-pool architectures.

Chapter 5 Fruit Fly: Investigates the biological mechanisms of fruit flies and how their distributive behavior can be applied to solve complex computational problems.

Chapter 6 Literature Survey: Reviews existing research and literature concerning the application of fruit fly optimization algorithms in various scheduling and computational domains.

Chapter 7 Present Works: Describes the methodology for optimizing RBF neural networks using aFOA and the MIV-based variable selection process.

Chapter 8 Framework and Technology: Explains the software tools, specifically MATLAB and MemBrain, used for implementing and analyzing the proposed algorithms.

Chapter 9 Result and Discussion: Presents the experimental results, numerical testing, and performance comparisons of the proposed algorithm.

Chapter 10 Conclusion: Summarizes the major contributions of the research and identifies potential future work and challenges in the field.

Keywords

Radial Basis Function (RBF), Neural Network, Fruit Fly Optimization Algorithm (aFOA), Mean Impact Value (MIV), Variable Selection, Distributed Computing, Back-Propagation, Parallel Processing, Swarm Intelligence, Optimization, Modeling, Simulation, MATLAB, MemBrain, Set-Streaming Stream-Shop Scheduling.

Frequently Asked Questions

What is the primary focus of this research?

The research focuses on the optimization of Radial Basis Function (RBF) neural networks using an amended Fruit Fly Optimization Algorithm (aFOA) to enhance training efficiency and variable selection accuracy.

What are the central thematic areas covered?

The work integrates concepts from biological inspiration (fruit flies), distributed computing systems, artificial neural network architectures, and swarm intelligence-based optimization techniques.

What is the main objective of the thesis?

The primary objective is to develop a more efficient model for RBF neural networks that can perform robust variable selection, thereby reducing computational costs and improving the prediction precision of complex, nonlinear systems.

Which scientific methodology is employed?

The researcher uses an amended Fruit Fly Optimization Algorithm (aFOA) combined with the Mean Impact Value (MIV) evaluation method to optimize the network structure and screen influential independent variables.

What does the main body of the work cover?

The main body covers theoretical foundations of neural networks, distributed systems architecture, the logic behind the fruit fly algorithm, and experimental validation using data sets to demonstrate the effectiveness of the aFOA-RBF approach.

Which keywords characterize this work?

Key terms include RBF Neural Networks, aFOA, MIV, Variable Selection, Distributed Computing, Swarm Intelligence, and Set-streaming Stream-shop Scheduling.

How does the fruit fly behavior inform the optimization process?

The algorithm mimics the foraging behavior of fruit flies, specifically their ability to sense food sources using osphresis and vision, to navigate the search space and find global optima more effectively than traditional methods.

What role does the MemBrain simulator play in this research?

MemBrain serves as a flexible graphical editor and simulator for neural networks, allowing the author to design, train, and test the proposed RBF network architectures and generate C-code for production implementation.