Machine Learning ( Associate Lvl )

30 hr

The program is structured into 10 sessions, each lasting 3 hours. Each session will blend theoretical explanations with practical hands-on labs. The following outline highlights the key topics covered:

1. Session 1: Introduction to Machine Learning and Python Fundamentals

• • What is Machine Learning? (Definition, History, Applications)

  • Types of Machine Learning: Supervised, Unsupervised, Reinforcement Learning

  • The Machine Learning Workflow: Data Collection, Preprocessing, Model Training, Evaluation, Deployment

  • Introduction to Python: Variables, Data Types, Operators, Control Flow (if/else, loops)

  • Introduction to NumPy: Arrays, Array Operations

  • Hands-on Project: Basic Python and NumPy Exercises

            2. Session 2 : Essential Math for Machine Learning (Part 1: Linear Algebra)

• • Vectors and Matrices: Definitions, Operations (Addition, Subtraction, Multiplication)

  • Transpose, Inverse, Determinant of a Matrix

  • Eigenvalues and Eigenvectors (Conceptual Introduction)

  • Linear Equations and Systems of Equations

  • Hands-on Project: Implementing Linear Algebra operations using NumPy. Solve a simple system of linear equations.

           3. Essential Math for Machine Learning (Part 2: Calculus and Statistics)

• • Introduction to Calculus: Derivatives and Integrals (Conceptual Understanding)

  • Probability: Basic Concepts, Probability Distributions (Normal, Binomial)

  • Descriptive Statistics: Mean, Median, Mode, Variance, Standard Deviation

  • Inferential Statistics: Hypothesis Testing (Brief Overview)

  • Hands-on Project: Calculating descriptive statistics using NumPy and Pandas. Plotting probability distributions.

           4. Session 4: Data Preprocessing with Pandas

• • Introduction to Pandas: Series and DataFrames

  • Data Loading and Inspection

  • Data Cleaning: Handling Missing Values, Removing Duplicates

  • Data Transformation: Feature Scaling (Normalization, Standardization), Encoding Categorical Variables (One-Hot Encoding)

  • Hands-on Project: Cleaning and preprocessing a real-world dataset using Pandas.

           5. Session 5: Supervised Learning: Regression

• • Introduction to Supervised Learning

  • Linear Regression: Simple Linear Regression, Multiple Linear Regression

  • Polynomial Regression

  • Evaluation Metrics for Regression: Mean Squared Error (MSE), R-squared

  • Overfitting and Underfitting

  • Hands-on Project: Building and evaluating a Linear Regression model using Scikit-learn on a sample dataset.

            6. Session 6: Supervised Learning: Classification

• • Logistic Regression

  • K-Nearest Neighbors (KNN)

  • Decision Trees

  • Evaluation Metrics for Classification: Accuracy, Precision, Recall, F1-Score, Confusion Matrix

  • Hands-on Project: Building and evaluating a Logistic Regression and KNN model using Scikit-learn on a classification dataset.

           7. Session 7: Model Evaluation and Selection

• • Cross-Validation: K-Fold Cross-Validation

  • Hyperparameter Tuning: Grid Search, Randomized Search

  • Model Selection Criteria: Bias-Variance Tradeoff

  • Regularization (L1 and L2 Regularization - Conceptual)

  • Hands-on Project: Implementing cross-validation and hyperparameter tuning for a classification model.

          8. Session 8: Unsupervised Learning: Clustering

• • Introduction to Unsupervised Learning

  • K-Means Clustering

  • Hierarchical Clustering

  • Evaluation Metrics for Clustering: Silhouette Score

  • Hands-on Project: Applying K-Means clustering to a dataset and evaluating the results.

         9. Session 9: Feature Engineering and Feature Selection

• • Feature Engineering Techniques: Creating new features from existing ones

  • Feature Selection Techniques: Filter Methods, Wrapper Methods

  • Dimensionality Reduction (PCA - Conceptual Introduction)

  • Hands-on Project: Applying feature engineering and selection techniques to improve model performance.

        10. Session 10: Project Implementation and Course Review

• Comprehensive Project: Trainees work on a more complex ML project that integrates the concepts learned throughout the course (e.g., predicting customer churn, classifying images and predicting house prices).

• Model Deployment (Brief Overview)

• Review of Course Concepts

• Total Credit Hours: 30
• Session Length: 3 hours per session
• Number of Sessions: 10
• Delivery Method: Remotely

1. Upon completion of this course, trainees will be able to:

• Explain the different types of Machine Learning problems and their applications. (Regression, Classification, Clustering)

• Describe the mathematical foundations underlying common ML algorithms.

• Write Python code to implement and train ML models using Scikit-learn.

• Prepare and preprocess data for Machine Learning tasks. (Cleaning, Transformation, Feature Scaling)

• Select appropriate evaluation metrics for different ML problems.

• Tune hyperparameters to optimize model performance.

• Build and deploy basic ML models for practical applications.

• Communicate the results of ML analysis effectively.

• Demonstrate an understanding of the strengths and weaknesses of different ML algorithms.

• Possess the necessary knowledge and skills to confidently progress to Deep Learning courses.