ABSTRACT
The artificial intelligence (AI) domain grows every day with new algorithms and architectures. Artificial Neural Networks (ANNs), a branch of AI has become a very interesting domain since the eighties when the back-propagation learning algorithm and the feed-forward architecture were first introduced. As time passed, ANNs were able to solve non-linear problems, and were being used in classification, prediction, and representation of complex systems. However, ANN uses a black box learning approach – which makes it impossible to interpret the relationship between the input and the output. Discrete Event System Specification (DEVS) is a mathematical well-defined formalism that can be used to model dynamic systems in a hierarchical and modular manner; it can automatically generate simulators for the described DEVS models. Combining ANN and DEVS, we can model the complex configuration of ANNs and express its internal workings. In this thesis, we are extending the DEVS-Based ANN proposed by Toma et al [1] for comparing multiple configuration parameters and learning algorithms. The DEVS model is described using a visual modeling language known as High Level Language Specification (HiLLS) for a clear understanding. This approach will help users and algorithm developers to test and compare different algorithm implementations and parameter configurations of ANN.
TABLE OF CONTENTS
CHAPTER ONE
1.0 INTRODUCTION
11.1. Context
11.2. Research Objectives
1.3. Related Works
1.3.1. Abstraction of Continuous System to Discrete Event System Using Neural Network
1.3.2. Identification of Discrete Event Systems: Using the Compound Recurrent Neural Network: Extracting DEVS from Trained Network
1.3.3. Neuro-DEVS, an Hybrid Methodology to describe Complex Systems
1.3.4. Dynamic Neuronal Ensembles (DNE): Neurobiologically Inspired Discrete Event Neural Networks
1.3.5. A New DEVS-Based Generic Artificial Neural Network Modeling Approach
1.4. Approach Adopted
1.5. Organization of Work
CHAPTER TWO
2.0 STATE OF THE ART
2.1. Artificial Neural Networks (ANN)
2.1.1. History
2.1.2. Architecture
2.1.3. Activation Functions
2.1.4. Learning Algorithms
2.1.4.1. Standard Back Propagation (BP) Algorithm
2.1.4.2. Back Propagation with Momentum Algorithm
2.1.4.3. Silva and Almeida (SA) Algorithm
2.1.4.4. Delta-Bar-Delta Algorithm
2.1.4.5. Quickprop Algorithm
2.1.4.6. Resilient Back propagation
2.1.5. Applications of ANN
2.2. Discrete Event System Specification (DEVS)
2.2.1. The DEVS Modeling
2.2.1.1. Atomic Classic DEVS Model
2.2.1.2. Coupled Classic DEVS Model
2.2.2. The DEVS Simulation
2.2.3. DEVS SimStudio Simulation Package
2.3. High Level Language for System Specification (HiLLS)
2.3.1. HiLLS Architecture
2.3.2. Concrete Syntax of HiLLS
2.3.3. HiLLS Example: Single Lane Road Model
CHAPTER THREE
3.0 DEVS- BASED ANN
3.1. DEVS-Based ANN Approach
3.1.1. DEVS-Based ANN Design
3.1.2. Feed-Forward Calculations Model Set
3.1.2.1. Non-Calculation Layer Atomic Model
3.1.2.2. Calculation Layer Atomic Model
3.1.3. Back-Propagation Learning Model Set
3.1.3.1. Error-Generator Atomic Model
3.1.3.2. Delta-Weight Atomic Model
3.2. HiLLS Description of DEVS-Based ANN
3.2.1. Input Generator (IGEN)
3.2.2. Non-Calculation Layer Atomic Model (NC)
3.2.3. Calculation Layer Atomic Model (CAL)
3.2.4. Target Generator (TGEN)
3.2.5. Error Generator (ERR)
3.2.6. Delta-Weight Atomic Model (DW)
3.2.7. DEVS-Based ANN Coupled Model
3.3. SimStudio Implementation
3.4. User Interface
CHAPTER FOUR
4.0 APPLICATION OF DEVS-BASED ANN
4.1. Presentation of the Case Studies
4.2. Data Extraction
4.2.1. Raw Data Presentation
4.2.2. Data Normalization
4.2.2.1. Statistical or Z-Score Normalization
4.2.2.2. Min-Max Normalization
4.3. Results
CHAPTER FIVE
5.0 CONCLUSION
5.1. Summary of Work Done
5.2. Pros and Cons
5.3. Future Works
CHAPTER 1
1.0 INTRODUCTION
1.1. Context
Modeling and Simulation (M&S), the third pillar of science is a paradigm that provides a way of obtaining the behavior of the representation of an object in real life without doing physical experiments. As introduced by the theory of Modeling and simulation [2], there are four major important concepts of M&S. The concepts are defined below:
a) System: is a well-defined object in the real world under specific conditions that we are interested in modeling.
b) Experimental Frame (EF): is a specification of the conditions within which the system is observed or experimented. It is realized as a system (with generators, acceptors and transducers) that interacts with the source system to obtain data of interest under specified conditions.
c) Model: is an abstract representation of the structure and properties of a system at some particular point in time or space intended to promote understanding of the real system.
d) Simulation: is the execution of a model over time in order to get the information about the changes in the behavior of the system during executions.
Modeling complex systems requires a robust formalism. The Discrete Event System Specification (DEVS) formalism [3] that was introduced in the early 70’s is a theoretically well-defined formalism for modeling discrete event systems in a hierarchical and modular manner. It allows the behavior modeling of complex systems.
Artificial Neural Networks (ANN) is a branch of artificial intelligence that became popular in the eighties when the back-propagation algorithm [4] for multilayer feed-forward architectures was introduced. It is widely known that classical neural networks, even with one hidden layer, are universal function approximators [5]. ANNs became widely applicable for real applications when it had the capabilities to solve non-linear problems. It is used for modeling of complex optimization problems such as classification, prediction and pattern recognition.
Artificial neural network is capable of modeling complex non-linear systems using adaptive learning mechanism to derive meaning from complicated or imprecise data with a high degree of accuracy. However, ANN uses a black box learning approach – when the general architecture is defined, you almost don’t have an idea of how the output is produced. To overcome this, DEVS is combined with ANN to express the relationship between the input and output. Combining DEVS and ANN is possible because ANNs are by default using discrete events i.e. the network is always waiting to an input event to generate an output one. Toma et al [1] proposed an approach for the describing the structure of ANN with DEVS known as DEVS-Based ANN. This approach was said to be able to facilitate the network configuration that depends a lot on ANN.....
================================================================
Item Type: Project Material | Size: 77 pages | Chapters: 1-5
Format: MS Word | Delivery: Within 30Mins.
================================================================
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.