| 1 |
Introduction: Explanation of the significance and purpose of the lesson, and its role in project implementation. |
|
| 2 |
Principles of programming: Exploring the fundamental principles of programming using MATLAB, with a focus on applying them to project-based learning. |
|
| 3 |
Neural Network Fundamentals: Defining neural networks and exploring their problem-solving capabilities, highlighting their distinctions from other mathematical methods. |
|
| 4 |
Artificial Neural Network Structure: Exploring the components of artificial neural networks, including neurons and their relationship to the human brain, as well as the comparison between the structure of natural and artificial neurons. |
|
| 5 |
Types of Artificial Neural Networks: Providing a general introduction to various neural networks that are applicable in the field of mechanization. |
|
| 6 |
Implementing Neural Networks in the MATLAB Environment: Utilizing MATLAB's graphical user interface (GUI) and the nftool tool for developing and deploying neural network models. |
|
| 7 |
Implementing Neural Networks in the MATLAB Environment: Utilizing MATLAB's graphical user interface (GUI) and the nftool tool for developing and deploying neural network models. |
|
| 8 |
Various Stages of Neural Network Operation: Gaining practical knowledge of training, validation, and testing concepts through hands-on examples in MATLAB. |
|
| 9 |
Training Algorithms: Exploring and analyzing the performance of various training algorithms for Multilayer Perceptron (MLP) neural networks. |
|
| 10 |
Problem Solving and Practical Case Studies in the Field of Mechanization: Addressing and evaluating real-world problems and practical scenarios within the domain of mechanization. |
|
| 11 |
Midterm Examination: Conducting a comprehensive assessment during the middle of the course to evaluate students' understanding and progress. |
|
| 12 |
Practical Implementation of Neural Networks in MATLAB: Introducing functional functions and their programming methods for practical implementation of neural networks. |
|
| 13 |
The syllabus encompasses the following topics: 1. Practical Implementation of Neural Networks in MATLAB: Introducing functional functions and their programming methods for practical implementation of neural networks. 2. Solving a Real Problem: Applying the learned concepts and techniques to solve a real-world problem using MATLAB. |
|
| 14 |
Evaluation Criteria for Neural Network Accuracy: Introducing error criteria and statistical measures for evaluating the accuracy of neural network performance during the training and testing phases. |
|
| 15 |
RBF Neural Network Part 1: Introduction to the Parameters of the RBF Neural Network. |
|
| 16 |
RBF Neural Network Part 2: Implementing RBF in MATLAB and evaluating the accuracy of its performance. |
|
| 17 |
RBF Neural Network Part 3: Implementing RBF in MATLAB and assessing the accuracy of its performance. |
|
| 18 |
Introduction to Neuro-Fuzzy Concepts: Gaining familiarity with the fundamental principles and concepts of neuro-fuzzy systems. |
|
| 19 |
ANFIS Implementation: Practical application and implementation of Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for solving problems. |
|
| 20 |
Methods for solving classification problems using artificial neural networks |
|
| 21 |
Problem Solving and Reviewing Articles in the Field of Neural Networks: Addressing and analyzing problems related to neural networks, as well as reviewing relevant articles in the field to gain a deeper understanding of current research and developments. |
|
| 22 |
Problem Solving and Reviewing Articles in the Field of Neural Networks: Addressing and analyzing problems related to neural networks, as well as reviewing relevant articles in the field to gain a deeper understanding of current research and developments. |
|