- Learn from the most popular areas of Machine Learning to the most useful algorithms in 5 days
- Get one step ahead by understanding the most useful methodologies in business
- A unique introductory course to better understand “Machine Learning”, one of the biggest fields of the AI era
- Makes it easy to understand both theoretical and practical approaches of Machine Learning and Artificial Intelligence technologies that affect our lives the most
- Made from resources from the best schools in the world and the best books in the field
Why Take This Course?
This course is for anyone who wants to take the first step into the world of Artificial Intelligence and Data Science by learning the fundamentals of Machine Learning.
In this course which Python programming language will be used, after the basic theoretical overview of Machine Learning, approaches to Regression and Classification problems which are the problem types of Supervised Learning, increasing the performance of these approach techniques will be covered and real-life projects will be developed. Afterwards, with Decision Trees, the deeper concepts will be covered. In addition to Decision Trees, the Ensemble Learning method, where we can combine different models that are frequently used in real life and create new models, will be discussed. On the last day of our course, the clustering method in Unsupervised Learning will be discussed and many concepts of Machine Learning will be learned to the full within 5 days.
Finally, we support your development process by giving you quiz assignments. When the project is finished, you will have 2 end-to-end projects related to Regression and Classification. Thus, you will not only leave what you have learned in theory, but you will also be able to improve yourself practically. In this way, you will be able to add your projects to platforms such as GitHub and Kaggle and expand your portfolio.
You are invited to join our Introduction to Machine Learning Hub and use this space to discuss topics related to the course, share interesting and relevant material and links, ask questions and engage with peers.
All Our Programs Include
- A joint certificate issued by Global AI Hub for each successful learner
- Additional access to active mentoring by Global AI Hub experts
- The certificate you will earn in this training is valid for privileged membership applications under the CoreRelation Program
- Thanks to the Swiss-based AI Business School and the «10million.AI» project this course is free
- It is part of the national education campaigns aiming at educating more than 10 million learners for free on AI and other digital technologies
Part of the following learning paths
- Welcome to Introduction to Machine Learning Course
- What is the Place of Machine Learning in the World of Artificial Intelligence?
- Why Do We Need Python for Machine Learning?
- Key Distinction Between Traditional Software Projects and Machine Learning Projects
MODULE 1 – INTRODUCTION
- What is Machine Learning?
- Machine Learning Disambiguation
- Types of Machine Learning
- Machine Learning Algorithms
- Machine Learning Applications
- Mathematics in Machine Learning
- Lineer Algebra
- Data Science
- What is Data Science?
- Feature Engineering
- End-to-End Model Training Steps
- Seeing the Big Picture
- Data Collection
- Exploratory Data Analysis (EDA) and Visualization
- Data Preprocessing
- Model Selection and Model Training
- Success Metrics
- Machine Learning Terminology
- Bias/Variance Tradeoff
- Early Stopping
- Batch size
- Tools Used in Machine Learning
- Sci-kit Learn
MODULE 2 – REGRESSION
- What is Regression?
- Regression Types
- Simple Linear Regression
- Multiple Linear Regression
- Polynomial Regression
- Measuring the Performance of Our Regression Model
- Error Concept
- Mean Absolute Error (MAE)
- Mean Squared Error (MSE)
- Errors That May Be Encountered in Model Training
- Underfitting & Overfitting
- Bias/Variance Tradeoff
- Error Reduction Methods
- Train-test-validation Split
- Early Stopping
- Gradient Descent
- L1 Lasso
- L2 Ridge
- Hyper-parameter Definitions
- Cross Validation
- Project 1: Sepal Length Estimation with Iris Dataset – Regression Project
MODULE 3 – CLASSIFICATION
- What is Classification?
- Logistic Regression
- Activation Functions
- Sigmoid Function
- Softmax Function
- Measuring the Performance of Classification Model
- Error Concept
- Confusion Matrix
- Accuracy, Precision, Recall, F1 Score
- Classification Threshold
- ROC(Receiver Operating Characteristics) & AUC (Area Under the Curve)
- Commonly Used Classification Algorithms
- K-Nearest Neighbors
- Support Vector Machine
- Decision Trees
- Project 2: Prediction of Cancer with the Breast Cancer Dataset – Classification Project
MODULE 4 – DECISION TREES
- What are Decision Trees?
- Decision Trees Application
- How Are Decision Trees Calculated?
- Decision Trees Advantages
- Information Gain
- Gini Index
- Visualization of Decision Trees
MODULE 5 – UNSUPERVISED LEARNING
- What is Unsupervised Learning?
- Why Use Unsupervised Learning?
- Unsupervised Learning Algorithms
- Visualization and Dimension Reduction
- Principal Component Analysis (PCA)
- What is Clustering?
- Clustering Types
- Affinity Propagation
- Hierarchical Cluster Analysis (HCA)
- Density-based Spatial Clustering (DBSCAN)
- K-Means Clustering
- Elbow Method
- Mini-Batch K-Means
- Practical Use Of What Has Been Learned
- Further Projects
- What’s Next?
The course includes a series of lessons that lead you through the content in small, bite-sized learning blocks. Each lesson includes exciting video sessions followed by thought-provoking assessment questions.
- Video sessions have to be marked as complete and can be accessed freely after the completion of each lesson.
- Assessment questions are graded for the calculation of certification progress.
- Each day has a “Materials” section to help you revise the topics that are seen that day.