Introduction to AI and ML
Course Overview:
Welcome to the world of Artificial Intelligence and Machine Learning! This course is designed for students who are curious about how machines learn, think, and make decisions — and want a solid foundation in the core concepts and techniques of AI/ML. Through real-world examples and hands-on projects, you’ll explore how AI is transforming industries like healthcare, finance, robotics, gaming, and more. This is your first step into one of the most exciting and fast-growing fields in technology.
What You Will Learn:
-
What is AI and ML: key concepts, history, and real-world impact
-
Types of Machine Learning: supervised, unsupervised, reinforcement learning
-
Linear regression and classification models
-
Decision trees, random forests, and k-nearest neighbors
-
Clustering techniques (e.g., k-means)
-
Evaluation metrics (accuracy, precision, recall, confusion matrix)
-
Introduction to Neural Networks
- Using Python and scikit-learn for model building
-
How to prepare and clean data for machine learning
-
Hands-on projects: image classification, spam detection, game-playing AI
-
Ethical considerations in AI
Course Features:
-
Hands-on Exercises: Build, train, and test real AI/ML models with guided projects.
-
Real-World Examples: Learn how AI/ML is used in apps, games, self-driving cars, and more.
-
Live Support: Access to Q&A sessions and instructor guidance.
-
Flexible Learning: Recorded sessions and resources available anytime.
Ideal For:
-
High school, college students and professionals interested in AI/ML
-
Beginners with basic Python knowledge who want to build smart applications
-
Future data scientists, AI engineers, and tech innovators
-
Anyone curious about the real-world impact and future of AI
Duration:
About 10 weeks, with 1 session per week (1 hours per session)
Prerequisites:
Basic understanding of math (especially algebra) and some experience with Python programming is required.
Materials Included:
-
Access to comprehensive video lectures
-
Python code examples and exercises
-
Datasets and project templates
-
Additional reading and reference materials
Outcome:
By the end of this course, you will understand how AI and ML work, be able to build and evaluate simple machine learning models, and gain the confidence to explore more advanced AI topics in the future.
Join Us Today and Start Your AI/ML Journey!
Curriculum
- 11 Sections
- 83 Lessons
- 0m Duration
Introduction to AI and ML
- Introduction to AI
- Introduction to Machine Learning
- Overview of AI and Machine Learning
- Overview of Machine Learning Workflow
Math ( Statics ) Foundation
- 🎲 Introduction to Probability
- 🎓 Basic Rules of Probability
- What is Conditional Probability?
- 📘 Understanding Bayes’ Theorem
- 🎯 Frequentist vs Bayesian Probability / Inference
- 📊 Probability Distribution & Gaussian Distribution
- 📘 Mean and Variance
- 📘 Entropy, Cross-Entropy, and KL Divergence
- Advanced topic: 📘 Entropy and Information Bits
- Statistics for Machine Learning Engineers: A Comprehensive Tutorial
- Statistics and Math for AI/ML and Deep Neural Networks (DNNs)
- Advanced topic: P/NP
Data Analysis
- Introd Jupter
- Writing and Using Markdown in Jupyter Notebook
- VSCode and Jupternotebook
- Analyzing Numerical Data with NumPy
- Analyzing Data Using Pandas
- Visualization with Matplotlib
- Visualization Using Seaborn
- Exploratory Data Analysis
Machine Learning Fundamentals
- 🧠 Overview of Machine Learning Frameworks
- ✅ Why Can Machine Learning Be Treated as a Probability Problem?
- what is Statistical Learning
- What is difference between Statistical Learning and Machine Learning
- Dataset Splitting: Training, Test, and Validation
- MLE and MAP in Machine Learning
- 📘 : Loss Functions in Machine Learning
- 📘 How Loss Functions Connect with MLE, MAP, and Priors
- Regression vs. Classification Problems
- 📘 Supervised Learning
- Advanced topic: Supervised learning generative and discriminative approach
- Supervised Learning: Linear Regression
- Advanced topic: Why Use Mean Squared Error (MSE) in Regression?
- Supervised Learning – Classification
- Classification: Logistic Regression
- Advanced topic: multi-category classification
- Advanced topic: class imbalance
- What is the Likelihood Function for Logistic Regression (Logit)?
- Difference Between Logistic Regression and Linear Regression
- What are Non-Parametric Methods in Machine Learning?
- Naive Bayes Classifier: Detailed Explanation with Example
- What is Linear Discriminant Analysis (LDA)?
- K-Nearest Neighbors (KNN) Algorithm
Model evaluation
- Model Evaluation: Performance Metrics and Error
- Understanding Bias and Variance
- Advanced topic: Understanding Variance More Deeply
- Overfitting, Underfitting
- False Positives, False Negatives, and AUC-ROC Curve
- Advanced topic: P-R curve vs RoC curve
- Hypothesis Testing
- Advanced topic: Relationship Between Hypothesis Testing and Machine Learning
Resampling methods
- How to Sample from a Probability Distribution
- Resampling Methods
- Why Do We Need Cross-Validation?
- Bootstrap
- Advanced topic: why sample 100 points even if we only have 100 points in the original data.
- How Bootstrap Helps in Machine Learning Model Evaluation
- Advanced topic: Bootstrap vs. Cross-Validation
- Dimension Reduction Methods
Advanced ML
- Supervised Learning – Decision Trees and Random Forests
- Advanced topic: Tree-Based Methods
- Support Vector Machine (SVM)
- 📘 Markov Models in Machine Learning
- 📚 Common Modeling Principles (Organized by Philosophy)
- 📘 Maximum Entropy Model
unsupervisied learning
- Unsupervised Learning: Clustering
- Discussion: can unsupervised method handle regression and classification problem?
- 🧠 What is Semi-Supervised Learning?
- Advanced topic: why the Expectation-Maximization (EM) algorithm can estimate the correct parameters
Neural Networks and DNN
- Neural Networks and Deep Learning
- 🤔 Should Machine Learning Be Treated as a Probability Problem or an Optimization Problem
- Introduction to Neural Networks
- Backward Propagation (Backpropagation)
- Advanced topic: BP without closed math formula
- Deep Learning and Convolutional Neural Networks (CNNs)
Reenforcement Learning
- Reinforcement Learning
AI in real world
- Advanced AI Techniques
- AI in the Real World
- Practical AI Applications
Related Courses
USACO fundemntal: Introduction to Algorithm I
Basic Algorithms
Easy to understand
Tailed for USACO
