General
🌟 Welcome to the Course
Embark on an exciting AI journey! From fundamentals to real-world applications, this course equips you with the skills to design intelligent systems and solve complex problems.
👥 Who Must Enroll
This course is perfect for:
- Engineering and computer science students
- Tech enthusiasts eager to understand AI
- Anyone who wants to apply AI in real-world problems
💡 Why Must Enroll
AI is transforming industries worldwide. By enrolling in this course, you will:
- Gain essential AI skills and hands-on experience
- Learn to design intelligent solutions for complex problems
- Stay ahead in the modern workforce
📖 Course Synopsis
Students will explore fundamental concepts of AI, modern techniques, and tools to design intelligent systems that solve real-world problems. Topics include search & optimization algorithms, machine learning, deep learning, as well as AI applications, history, philosophy, ethics, and the future of AI.
🎯 Course Outcomes
- Apply AI principles, models, and algorithms to solve complex problems
- Analyze AI concepts and techniques for problem-solving
- Design solutions for complex engineering problems using AI techniques
🗂 Modules in This Course
- IMJC4001-1: Introduction to Artificial Intelligence
- IMJC4001-2: Artificial Intelligence System
👩🏫 Instructors
Ir Dr. Marni Azira Markom
Assoc. Prof. Ts. Dr. Amiza Amir
📝 Instructions for Students
- Go through each module and understand the learning objectives.
- Watch the teaching videos provided for each subtopic.
- Download and review lecture notes for deeper understanding.
- Complete quizzes or exercises after each module to assess your knowledge.
- Engage in discussions or forums if available to clarify doubts and share insights.
Module 1: Introduction to Artificial Intelligence
📘 Topic 1: Artificial Intelligence Overview
Instructor: "Welcome to the fascinating world of AI! Explore the foundation, history, and applications carefully, and think about where AI is impacting your life."
AI Overview
Let's understand the basics of AI first. Focus on the definition, history, and different forms of learning in AI.
AI Application
Observe different AI applications in real life. Think about which applications are most relevant to your studies or future career.
Summary and Quiz
Now that you have explored AI concepts and applications, review this summary carefully and attempt the quiz to reinforce your understanding.
📘 Topic 2: Practical Considerations, Hyperparameters, and Performance Evaluation
Instructor: "Always remember, tuning hyperparameters and evaluating models properly is the key to achieving reliable AI solutions.
AI Programming and Tools
Explore the main programming languages like Python and R, and popular tools such as TensorFlow, PyTorch, and Scikit-learn. Which one do you think is the most user-friendly for beginners?
Parameters and Hyperparameters
Think about the difference: parameters are learned by the model (like weights), while hyperparameters are set before training (like learning rate or number of layers). Why do you think hyperparameters can greatly affect the final performance?
Performance Evaluations
Accuracy, precision, recall, and F1-score are commonly used for classification, while RMSE and MAE are used for regression. Which metrics do you think are most important for a healthcare AI system?
Summary and Quiz
Reflect on the importance of choosing the right tools, setting appropriate hyperparameters, and selecting the best evaluation metrics. These decisions often determine the success or failure of an AI project.
📘 Topic 3: Machine Learning
Summary of the Topic: This topic introduces the basics of Machine Learning (ML), its main processes, learning types (supervised, unsupervised, semi-supervised, reinforcement), and example algorithms that solve real-world AI problems.
Instructor: "Let's dive into the world of machine learning! Observe each model carefully and think about how you would apply them in practice."
Machine Learning Process
ML typically follows a cycle: data collection, preprocessing, model selection, training, evaluation, and deployment. Each step is crucial for success.
Supervised Learning
Trains models with labeled data to make predictions. Common algorithms include ANN, Decision Tree, Random Forest, and K-Nearest Neighbors (KNN).
Unsupervised Learning
Finds hidden patterns or structures in unlabeled data. Techniques include K-Means, Hierarchical Clustering, and PCA.
Semi-Supervised Learning
Uses both a small amount of labeled data and a large amount of unlabeled data. Methods include self-training, co-training, and graph-based models.
Reinforcement Learning
Trains agents to make decisions through trial and error, using rewards and penalties. Examples include Q-Learning, Deep Q-Networks, and Policy Gradient methods.
Summary and Quiz
Great work! Now review the key concepts and challenge yourself with the quiz to reinforce your understanding.
📘 Topic 4: Deep Learning
Summary of the Topic: This topic introduces Deep Learning (DL) concepts, types of data (time series, images, tabular), neural network architectures, main tasks such as classification and prediction, and techniques like transfer learning.
Instructor: "Amazing! You've got the big picture now. Imagine being able to teach a computer to recognize patterns and make predictions just like a human brain—what possibilities excite you the most?"
Deep Learning Overview
Let's dive into the world of deep learning! Observe how neural networks can automatically extract features from raw data and think about where you could apply this.
Data Types for Deep Learning
Think about the different types of data you encounter: sequences, images, tabular data. How do you think deep learning handles each type differently?"
Neural Network Architectures
Observe these architectures: Feedforward (MLP), CNN for images, RNN/LSTM for sequences, and Autoencoders for feature learning. Which one would you choose for your problem?
Tasks in Deep Learning
Deep learning can handle classification, regression/prediction, and anomaly detection. Think about which task best fits your data.
Transfer Learning and Pretrained Models
Sometimes you don't need to train a model from scratch. Using pretrained models saves time and resources. Can you think of examples where this is helpful?
Summary and Quiz
Now, review the summary and complete the quiz to consolidate your understanding. Remember, applying these concepts will make you confident in building deep learning models.
🚀 Topic 5: AI Frontier Technologies
Summary of the Topic: This topic introduces advanced AI technologies shaping the future, including Generative AI, Quantum Machine Learning, and Explainable AI.
Instructor: "These frontier technologies represent the cutting edge of AI. Think about how they may influence your field of study or industry in the next 5–10 years."
Generative AI
Generative AI powers tools like ChatGPT and image creators. Reflect on how this technology might transform creativity, research, and business processes.
Quantum Machine Learning
Quantum Machine Learning combines quantum computing and AI, promising faster solutions to complex problems. Consider which industries may benefit most from this integration.
Explainable and Responsible AI
AI must be trustworthy and transparent. Think about why explainability and ethics are vital for real-world AI adoption, especially in healthcare, finance, and governance.
Summary and Quiz
You’ve explored Generative AI, Quantum Machine Learning, and Explainable AI. Remember their key ideas, future potential, and challenges. The quiz will check how well you understand and can apply them.
TEST
🎉 Congratulations! You’ve almost completed Module 1. Take two mock tests before attempting the real test. You must pass both mock tests before applying for the real one. 🚀
Mock Test 1Result: PendingMock Test 2Result: Pending