AI COURSE - INTRODUCTION TO MACHINE LEARNING

AI Course: Introduction to Machine Learning with Python for beginners

16 live online sessions with instructors, in classes of 7–15 people. For those who want to understand how Machine Learning models work, aiming to become a Junior Data Scientist or ML Engineer, or to move into AI.

Next class🔥 7 seats left

AI Online 07 · Starts Jan 23, 2027

Sat evenings, 19:00 – 21:30 (Vietnam time, GMT+7) · Live online, taught in Vietnamese

5,950,000 VND8,500,000 VND30% off for the first 5 people to register

✓ 100% refund if you cancel at least 15 days before the start date✓ Installment payments available

Students and instructors in a Big-O Coding class
⭐ 5.0 / 400+ Google reviews

AI Course tuition, schedule and duration

Ideal forPeople who want to understand how Machine Learning models work, aiming to become a Junior Data Scientist or ML Engineer, or to move into AI
LevelJunior / Entry-level
Duration16 main sessions + 8 tutoring sessions, 2 hours 30 minutes each
Programming languagePython
FormatOnline (live class, taught in Vietnamese), 7–15 students per class
Schedule1 session a week (Sat evenings), 19:00 – 21:30 (Vietnam time, GMT+7)
Start dateAI Online 07: Jan 23, 2027 (7 seats left)
Tuition5,950,000 VND (regular price 8,500,000 VND). 30% off for the first 5 people to register. Former students pay only 5,500,000 VND. Installment payments available
Free trial & refundFirst session free. 100% refund if you cancel at least 15 days before the start date (policy)
InstructorsHoàng Thiên Nữ, Lê Thảo Huyền, Phạm Phong Hào (our team)
Student results5.0 rating from 400+ Google reviews (reviews)

✨ Who the AI Course is for

  • ✓Want to understand in detail how Machine Learning models work, instead of just knowing how to call libraries.
  • ✓Aim to become a Junior Data Scientist or ML Engineer, or to switch careers into AI.
  • ✓Need a structured roadmap from AI and Algorithms experts with many years of experience.
  • ✓Want to keep up with the technology trends of the future (Neural Networks, LLMs).
  • ✓Need a highly interactive learning environment, with support from instructors and teaching assistants.
  • ✓Need weekly Office Hours to review and keep up with the hands-on practice.

📅 AI Course start dates and tuition

AI Online 07 Jan 23, 2027 · Sat evenings, 19:00 – 21:30 (Vietnam time, GMT+7) 🔥 7 seats left
8,500,000 VND
5,950,000 VND
30% off for the first 5 people to register
Former students pay only 5,500,000 VND
✅ First session free ✅ 100% refund if you cancel 15 days before the start date ✅ Pay in installments

What AI Course students say

“I'm a student of the Introduction to Machine Learning course at Big-O Coding, and I find the program designed to be quite accessible, even for people with no IT background like me.”
Linh Đăng NguyễnAI Course student
“The curriculum is complete, clear and detailed, from setting up the environment and using the libraries all the way to analyzing time and space complexity.”
Quỳnh TrầnAI Course student
“Personally, I find the course digs quite deep into the essence of the ML methods being applied, giving you enough knowledge to carry on researching by yourself.”
Phan HuấnAI Course student

Read more student reviews →

Reserve your seat in the AI Course

Big-O will confirm by Zalo and email within 30 minutes

More options: package, referrer, notes
Single course AI Course only 5,950,000 VND Breakthrough combo Bundle AI + Blue (35% off) ~10,400,000 VND
❌ Something went wrong. Please call us directly at 0937 401 483

100% refund if you cancel at least 15 days before the start date. Installment payments available.

✅

You're registered!

Big-O Coding has received your details.

We will contact you by phone and email within the next 30 minutes.

📞 Phone: 0937 401 483

💬 Email: admin@bigocoding.com

AI Course syllabus: 16 sessions of Machine Learning, from data to Deep Learning

From raw data to intelligent AI systems

Click to see the detailed syllabus
PART 1 - DATA FOUNDATIONS & MACHINE LEARNING BASICS
Lecture 01 - Data Preprocess and Visualization

Content: An overview of Data Science. Master the core libraries: Numpy (array processing), Pandas (basic data processing) and data visualization with Matplotlib & Seaborn.

Practice: Explore and analyze the real-world Netflix TV Shows dataset.

Lecture 02 - K-Nearest Neighbors (KNN)

Content: The concepts of Classification and Regression problems. A deep dive into the distance-based KNN algorithm for both problem types.

Practice: Tune model parameters and apply KNN to detect outliers.

Lecture 03 - Model Validation and Selection

Content: Model evaluation metrics: Confusion matrix, Accuracy, Precision, Recall, F-score, ROC-curve, MAE, MSE, RMSE, R2. Learn about the Bias-Variance trade-off and Cross-validation techniques.

Practice: Detect spam with KNN and improve accuracy by handling Stop words.

Lecture 04 - Linear Regression

Content: Explore linear functions and the loss function, and solve the optimization problem with the Least-Squares method. Techniques to prevent Overfitting with Regularization.

Practice: Build regression models (univariate & multivariate) to predict medical insurance costs. Apply Lasso Regression for feature selection.

PART 2 - OPTIMIZATION & PROBABILISTIC MODELS
Lecture 05 - Gradient Descent

Content: Derivatives and Gradients. Variants: Mini-batch GD, Momentum, Adaptive Learning Rate. Illustrated with the plant-watering Robot problem.

Practice: Implement Gradient Descent with Momentum yourself, from scratch.

Lecture 06 - Logistic Regression

Content: Binary classification with Sigmoid & Logloss. Multiclass classification with Softmax & Cross-Entropy loss. Optimization with Gradient Descent.

Practice: Apply Polynomial Transform to classify non-linear data.

Lecture 07 - Naive Bayes

Content: Review probability and statistics (Bayes' theorem, conditional probability). Apply the Bernoulli, Gaussian and Multinomial distributions to the Naive Bayes algorithm.

Practice: Sentiment Analysis: preprocess text data and build Multinomial Naive Bayes from scratch.

Lecture 08 - Mid-Term Project

Project: Loan Approval Prediction.

Goals: Apply the Data Preprocessing and EDA workflow and the models you have learned to solve a real-world business problem from start to finish.

PART 3 - ADVANCED MACHINE LEARNING & UNSUPERVISED LEARNING
Lecture 09 - Support Vector Machine (SVM)

Content: The concepts of the Maximal Margin Classifier and the Support Vector Classifier. The power of the Kernel trick to transform the data space.

Practice: Tune the hyperparameter C and use the Kernel trick for complex multiclass classification problems.

Lecture 10 - Decision Tree

Content: Decision Tree architecture. Build trees with Recursive Binary Splitting. The Gini Index and Entropy measures, and computing RSS for regression.

Practice: Use Decision Trees for Feature Selection and implement the algorithm with Information Gain.

Lecture 11 - Clustering

Content: Customer clustering with K-means. How to choose the optimal K. An introduction to K-means++ and Hierarchical Clustering.

Practice: Apply the Elbow method and use K-means to compress digital images.

Lecture 12 - Dimensionality Reduction

Content: The idea behind the PCA algorithm. Change of basis in vector space. How to find the optimal number of principal components.

Practice: Apply Eigenface to face recognition and compute the cumulative variance ratio.

PART 4 - DEEP LEARNING & HANDS-ON APPLICATIONS
Lecture 13 - Hyperparameter Tuning & Ensemble Methods

Content: Strengthen your models with Bagging (Random Forest), Boosting (AdaBoost, GradientBoost) and Stacking. Parameter search with Grid/Random Search and Bayesian Optimization.

Practice: Apply Ensemble Models together with Tuning to predict diabetes.

Lecture 14 - Neural Networks

Content: Step into the world of Deep Learning. The components of an ANN, Backpropagation. Tackle classic problems: Exploding/Vanishing gradients and Overfitting.

Practice: Build your first Neural Network with PyTorch on the Moon and MNIST datasets.

Lecture 15 - Advanced Feature Engineering & AutoML

Content: Advanced feature crafting techniques: Transformation, Extraction, Selection. Handling imbalanced data (Class imbalance). Automation with ML Pipelines and AutoML.

Practice: Combine all the processing techniques to optimize house price prediction.

Lecture 16 - Final Project & Career Talk

Activities: Final project presentation - the Insurance Regression problem.

Talkshow: Industry experts share career guidance, how to build an impressive Portfolio and the path to becoming a professional AI/Data Engineer.

🎁 EXCLUSIVE BONUS: AI ENGINEER TOOLKIT
🤖 AI-Assisted Coding

Master using ChatGPT / GitHub Copilot to generate code (boilerplate), optimize Python functions and write documentation (docstrings) automatically.

⚙️ Model Deployment Basics

A model on your own computer is not enough. Learn how to package machine learning models and deploy them as a web app with Streamlit.

📈 Kaggle Strategy

Analyze top-ranked Notebooks on Kaggle. Tips to "squeeze out" every bit of model performance in Data Science competitions.

🛠️ ML Pipeline Automation

Build professional engineering habits: bundle the whole workflow, from data processing to training, into clean, easy-to-maintain Scikit-Learn Pipelines.

🚀 Portfolio & Resume Coaching

1-on-1 review of how to structure a Data Scientist / AI Engineer CV so it gets through the resume screening (ATS) of major tech companies.

AI Course instructors

Hoàng Thiên Nữ
Hoàng Thiên NữInstructor, AI Project Lead
  • Top 15 ACM-ICPC HCMUS contest.
  • Third Prize in Vietnam Olympiad in Informatics.
  • Studied for a Master's degree at Soonchunhyang University.
  • PhD Candidate, Deakin University; MLE@Tinyfish.
Lê Thảo Huyền
Lê Thảo HuyềnInstructor, in charge of the AI project
  • Third Prize at the Vietnamese Mathematical Olympiad.
  • Research intern at EPFL through Summer@EPFL.
  • Master's in Data Science at EPFL.
  • Top 5 students graduating with the highest GPA in APCS HCMUS.
Phạm Phong Hào
Phạm Phong HàoInstructor, in charge of the AI project
  • Data Scientist at ANTSOMI CDP 365.
  • Former Data Scientist at FPT Corporation (CADS).
  • Former Data Scientist & Data Engineer at FPT Telecom (CADS).
  • Has served as a teaching assistant at CoderSchool.

Meet our instructors and teaching assistants →

Read ahead on our blog

See the Programming Handbook →

Frequently asked questions about the AI Course

What does the AI Course cover?

16 main sessions in 4 parts: data foundations and basic Machine Learning (data preprocessing, KNN, model evaluation, linear regression), optimization and probabilistic models (gradient descent, logistic regression, Naive Bayes), advanced Machine Learning (SVM, decision trees, clustering, dimensionality reduction, ensembles) and Deep Learning (neural networks, AutoML). Includes a midterm project and a final project, plus 8 tutoring sessions.

How do the online classes work, and how many students are in a class?

You learn live online with the instructor (live class, taught in Vietnamese), 1 session a week (Sat evenings), 19:00 – 21:30 (Vietnam time, GMT+7). Each class has 7–15 students.

Which programming languages are used?

Python.

How much is the tuition, and can I pay in installments?

5,950,000 VND (regular price 8,500,000 VND). 30% off for the first 5 people to register. Former students pay only 5,500,000 VND. Installment payments available.

Can I try a class first, and what if I cancel?

First session free. 100% refund if you cancel at least 15 days before the start date.

What level is the AI Course for?

Junior / Entry-level, using Python. The course goes from basic algorithms to Neural Networks and LLMs.

Ready to start your journey?

Enroll Now