A comprehensive machine learning track where students explore AI concepts, create ML models, and build intelligent applications using Python, while considering ethical implications of artificial intelligence.
For students interested in coding and machine learning, this program explores Machine Learning (ML) principles and real-world applications. Machine learning drives intelligent, responsive programs with real-world impact including self-driving cars, AI assistants, facial recognition, and predictive analytics. Students progress from exploring ML concepts to creating effective, unbiased models and building complete AI-driven applications with Python.
Students train and test an image recognition model using Teachable Machine. They learn to differentiate between testing and training datasets, understanding how training data supports machine learning. Students explore how ML models learn patterns from data and improve accuracy through proper training techniques.
Students create an ML model to classify text sentiment (positive, negative, neutral) and build a Scratch front-end to display output. They define sentiment analysis, describe real-world applications (social media monitoring, customer feedback), and recall the training process for text-based ML models.
Students build a face filter application using Machine Learning for Kids (MLFK) and Scratch. They explain how image recognition works for facial detection and recall the basics of the Viola-Jones algorithm. Students apply face detection to create interactive filters similar to social media applications.
Students create a voice recognition application using MLFK and Scratch. They identify examples and applications of voice recognition models (voice assistants, accessibility tools, transcription services) and understand how audio data is processed by ML models to recognize speech patterns.
Students explore "Big Data" and machine learning for dataset analysis. They define the scientific method, hypothesize which features in a dataset are significant, and understand how ML helps identify patterns in large datasets that humans cannot easily detect manually.
Students learn about predictive AI through the scientific method: hypothesize, test, and revise. They recall the scientific method steps, assess hypotheses with incoming data, and revise predictions based on model performance. Focus is on iterative improvement through data-driven insights.
Students plan a final AI project by documenting their idea for a custom ML model. They propose a machine learning application, identify required data types (text, image, sound), define training approach, and outline how their model will solve a specific problem or create value.
Students build and present their final AI project to classmates. They demonstrate their ML model, explain the training process, discuss model accuracy, and reflect on challenges solved. Students practice presenting technical concepts clearly and receive feedback on both model design and implementation.
Students learn basic Python syntax: print statements, input functions, and variables. They practice writing simple Python programs, understand data types (strings, integers, floats), and compare Python syntax to visual programming (Scratch). Focus is on transitioning from block-based to text-based coding.
Students write condition statements in Python using if/elif/else. They recall and apply syntax for conditional logic, create programs with branching behavior, and understand how conditions control program flow. Students translate conditional thinking from Scratch to Python text syntax.
Students use logical operators (AND, OR, NOT) in condition statements. They recall and apply operator syntax, create complex conditions combining multiple criteria, and understand operator precedence. Focus is on building sophisticated decision-making logic in Python programs.
Students write arrays (lists) and loops in Python, comparing to Scratch equivalents. They recall and apply list/loop syntax, understand when arrays are better than individual variables, and use for/while loops to iterate through data efficiently. Students manage collections of related data.
Students create reusable functions in Python with parameters and return values. They recall and apply function syntax, call functions from main scripts, and organize code into modular, maintainable pieces. Focus is on code reusability and reducing repetition through function abstraction.
Students plan a text-adventure game to be built in a Python notebook (Google Colab). They apply concepts learned: print/input, variables, conditions, loops, arrays, and functions. Students design game narrative, map decision trees, and outline code structure before implementation.
Students develop their Python text-adventure game project with instructor support. They implement planned features, debug code errors, test gameplay logic, and refine user experience. Focus is on applying all Python concepts learned to create a complete, playable text-based game.
Students debug and present their Python game to classmates. They identify and explain code sections, demonstrate gameplay, discuss technical challenges solved, and reflect on their learning journey. Students practice communicating Python concepts clearly and receive feedback on code quality and game design.
Students recap prior ML experience and propose new machine learning applications using MLFK. They recall previous ML projects, identify gaps or improvements, and brainstorm original AI applications. Students justify their proposal, define target users, and outline how their ML model will provide value.
Students collect training data in MLFK and build a model with ≥50% accuracy. They apply ML concepts learned, train and test models effectively, evaluate model performance, and iterate on training data to improve accuracy. Focus is on creating well-trained, unbiased ML models through proper data collection.
Students configure a front-end system using Python notebook (Google Colab). They create a Colab environment, connect to the MLFK backend, and establish the infrastructure for their AI application. Focus is on integrating ML models with user-facing interfaces.
Students write Python scripts to handle ML model results. They capture model predictions, process confidence scores, format output for users, and implement error handling. Focus is on creating a smooth pipeline from ML backend to frontend display.
Students build the user interface for their AI application. They design input mechanisms for data collection, create output displays for model predictions, add visual feedback for user interactions, and polish the overall user experience.
Students test their complete AI application and refine based on feedback. They evaluate model accuracy in real-world scenarios, identify edge cases, improve error handling, and optimize user experience. Focus is on creating robust, reliable AI applications.
Students share projects with classmates and collect feedback for revisions. They speak to code design decisions, reflect on development process, provide constructive peer feedback, and learn to evaluate AI applications from both technical and ethical perspectives.
Students finalize and present their ML project to classmates, teachers, and guests. They demonstrate the application, explain model training approach, discuss accuracy metrics, address ethical considerations, and reflect on the complete development journey. Students showcase mastery of ML concepts, Python programming, and AI application development.
ML models that classify images with measurable accuracy, trained on custom datasets and tested systematically.
Text classification systems that analyze emotional tone with Scratch-based user interfaces.
Interactive applications using facial recognition technology to apply filters and effects in real-time.
Audio-based ML models that recognize speech patterns and respond to voice commands.
Text-based games built with Python, demonstrating programming fundamentals and logic flow.
Full-stack ML projects combining trained models with Python frontends, achieving ≥60% accuracy.
This program is designed to build real-world AI skills, technical confidence, and ethical awareness. Rather than passively using AI tools, students learn how machine learning actually works, gaining hands-on experience with the same technologies shaping our future.
Students learn professional ML concepts: training, testing, accuracy evaluation, and bias detection used in industry AI applications.
Students master Python syntax, data structures, and program logic—foundational skills for computer science and data science careers.
Students consider ethical implications of AI: bias in training data, privacy concerns, and responsible AI development practices.
Model accuracy metrics provide clear, objective evidence of learning progress and technical skill development.
Students understand core machine learning concepts: training vs testing datasets, model accuracy, confidence scores, and bias detection. They explain how ML models learn from data and improve through iteration.
Students master Python fundamentals: variables, conditions, loops, arrays, and functions. They write clean, organized code and transition confidently from visual to text-based programming.
Students apply the scientific method to ML development: hypothesize, test, evaluate, and iterate. They make decisions based on data rather than assumptions.
Students create effective ML models by collecting quality training data, avoiding bias, testing systematically, and optimizing for accuracy. They achieve measurable performance metrics (≥60% accuracy).
Students integrate ML backends with Python frontends, creating complete applications. They understand the entire pipeline from data collection to user interface.
Students evaluate ethical implications of ML applications: data privacy, algorithmic bias, fairness, and responsible AI deployment. They develop critical thinking about technology's societal impact.
Students explain complex AI concepts clearly, present technical projects professionally, and discuss ML development processes with both technical and non-technical audiences.
Training, testing, accuracy evaluation, bias detection, and model optimization for image/text/voice recognition.
Variables, conditions, loops, arrays, functions, and text-based coding for AI application development.
Scientific method application, hypothesis testing, data analysis, and predictive modeling with ML tools.
Integrating ML models with frontends, handling results, creating user interfaces, and deploying complete systems.
Evaluating bias, considering privacy, discussing fairness, and developing responsible AI practices.
Debugging code, improving model accuracy, systematic testing, and iterative refinement through data.
For Level 1, no prior ML experience is required, but familiarity with basic coding (Scratch or similar) is helpful. For Level 2-3, completion of previous levels or equivalent Python knowledge is recommended.
This is real machine learning using industry-standard concepts and tools. Students work with actual ML models, measure real accuracy metrics, and learn principles used in professional AI development.
Students learn Python, the most widely-used language for machine learning and data science. Python skills transfer directly to professional AI development, web development, and computer science.
Progress is measured through model accuracy metrics (target: ≥60%), completed projects, code quality, and technical presentations. Each student builds a portfolio of working ML applications.
This program builds foundational skills for AI engineering, data science, machine learning research, software development, and any field leveraging artificial intelligence and data-driven decision-making.
Questions about enrollment or want to discuss your child's learning path?
Phone/WhatsApp/Zalo: 0902 776 753
Email: hello@techtutor.academy
Website: techtutor.academy
Hours: Mon-Fri 8:00-21:00 | Sat-Sun 8:00-20:00