WELCOME ALL !!
A free online Fundamentals of Artificial Intelligence (AI) course by Dr Airil Yasreen Mohd Yassin is designed to build a strong foundation in AI by introducing the fundamental mathematical principles behind today’s AI technologies.
Starting on 4 August 2026, classes will be held every Tuesday, 9:00–11:00 PM (Malaysia Time). The course is suitable for beginners and open to everyone interested in understanding AI from first principles, including students, researchers, educators, engineers, industry practitioners, and anyone interested in exploring the foundations of modern AI.
Throughout the course, participants will learn key topics including Neural Networks (CNN), Physics-Informed Neural Networks (PINNs), Large Language Models (LLMs) & Transformers, and Data Analytics. The course will provide insights into how AI systems are developed, how they learn from data, and the mathematical concepts that support modern AI applications.
1️⃣ For those who have not registered yet
Please complete your registration using the following link:
https://forms.gle/ArsRx4a35TpcSkum7
2️⃣ Join the WhatsApp Group
Please join the WhatsApp group for class updates, announcements, discussions, and learning resources:
https://chat.whatsapp.com/DqS4h7eJdVJ8LazYPR4sM5?s=cl&p=i&ilr=4
3️⃣ AI Learning Materials
The course modules and learning resources can be accessed through: https://github.com/msnm-official/ai_modules
WEEK 01
Introduction to AI and Neural Network Fundamentals
04 AUGUST 2026
In Week 1, we introduced you to the artificial intelligence landscape, exploring the relationships between AI, Machine Learning (ML), Deep Learning (DL), and Generative AI. We exposed you to various DL architectures—like Feedforward Neural Networks (FFNN), RNNs, CNNs, and Transformers—alongside practical application examples. Next, we shifted our focus to the core structure of a shallow neural network, specifically diving into a single hidden layer network. Together, we thoroughly examined fundamental concepts, including the roles of neurons, channel weights, and biases at each layer.
…
WEEK 02
Forward-Pass Processing and Activation Functions
SCHEDULED FOR 11 AUGUST 2026
Google meet link: meet.google.com/azb-jpjm-zdh
In our second week, we will delve into the neural network output calculation phase, known as the forward-pass process. We will guide you step-by-step through how data is processed, beginning with the multiplication of inputs and weights, followed by the summation process incorporating bias values. Additionally, we will cover the critical step of nonlinearization, which we introduce through activation functions like the Sigmoid and Tanh functions. Building on this mathematical foundation, you will understand exactly how we design network models to mimic exact solutions, such as simultaneous linear equation systems…
Note (Week 02)
Recorded Video (Part 1)
Recorded Video (Part 2)
WEEK 03
Backward-Pass and Gradient Descent Optimization
SCHEDULED FOR 18 AUGUST 2026
Week 3 focuses on the mechanics of training neural network parameters through the backpropagation or backward-pass process. We will introduce you to defining and calculating model errors, evaluating network performance using Loss Functions like Squared-Error and Mean-Squared Error. The highlight of our week will be applying the Gradient Descent optimization algorithm, which we use to minimize these calculated losses. Finally, you will learn how to apply the chain rule to calculate gradients, enabling us to iteratively update the network’s weight and bias parameters…
…
Note (Week 03)
Recorded Video (Part 1)
Recorded Video (Part 2)