Machine Learning Methods Training

Artificial intelligence (AI) is rising to become one of the most impactful technologies in the history of humanity, and so it is vital to individuals and companies looking to survive and succeed in the future to gain understanding and competency with this technology. Future leaders will be those who most effectively exploit AI.

Machine learning (ML) is the foundation of the most significant AI applications, including decision automation and generative algorithms such as ChatGPT. Understanding ML is key to understanding the real applications and limitations of AI.

The objective of the Machine Learning Methods course is to equip participants with the knowledge and skills to:

• Understand key data science concepts that underpin ML.
• Understand the definition and interaction of AI, ML and Statistics.
• Identify opportunities for the application of ML in their field.
• Assess complex data sets and prepare them for efficient and effective analysis.
• Implement ML algorithms for insight discovery and decision-making support.
• Apply and interpret predictive analytics: CART, Random Forest, TreeNet, and MARS.

Minitab statistical software is utilized in the class. This course has 7 modules, 44 lessons, and 4-8 lessons per module.  The course instructor is Alexander Bell, Ph. D.  Alex is available to answer any questions you may have and is happy to discuss course topics.  The on-line / on-demand version of the course is expected to take 30-35 hours to complete.  On-line access is included for 6 months.

Machine Learning Methods – Course Content

Course Introduction

Module 1: Introductory Concepts

1. AI and Machine Learning
2. Problems and Algorithms
3. Computer Programming
4. Data
5. Mathematical Notation
6. Training and Testing
7. Confusion Matrix
8. ROC and Regression Performance

Module 2: Statistical Methods

1. Basic Statistics
2. Probability
3. Inferential Statistics
4. Naïve Bayes

Module 3: Data Preprocessing

1. Real Datasets
2. Data Cleaning
3. Missing Data
4. Outlier Investigation
5. Transformation
6. Integration
7. Data Reduction
8. Principal Component Analysis

Module 4: Cluster Analysis

1. Clustering Theory
2. K-means
3. Hierarchical Clustering
4. Density Based Clustering

Module 5: Regression Modeling

1. Correlation
2. Simple Linear Regression
3. Multiple Regression
4. Stepwise Regression
5. Logistic Regression
6. Spline Functions
7. Regression Splines (MARS)

Module 6: Decision Tree Theory

1. Classification Trees
2. Purity Measures
3. Numerical Features
4. Pruning and Missing Data
5. Regression Trees

Module 7: Decision Tree Algorithms

1. Introducing CART
2. Applying CART
3. Bagging
4. Introducing Random Forest
5. Applying Random Forest
6. Gradient Boosting
7. Introducing TreeNet
8. Applying TreeNet

Why is this course important now?

In the modern world, the quantity of historical data being produced and stored has skyrocketed, alongside the computing power available to analyze this data. Thus, there has been a corresponding increase in the development and importance of AI, and the utilization of automated machine learning techniques.

To survive and thrive in this rapidly developing environment, it is vital that companies and businesses, and their employees, understand and have the skills and knowledge to utilize machine learning, to extract maximal value from their growing data sets and identify the emerging opportunities provided by AI.

This course directly meets these requirements, by giving participants a comprehensive overview of machine learning, its relation to AI, and its applications. It will equip participants with the knowledge and skills to understand how machine learning methods can be applied to their problems, including in-depth training in several popular techniques, and empower them to better understand the work they govern and discover opportunities for improvement.

Typical attendees

• Data analysts
• Data scientists
• Statisticians
• Research scientists
• Engineers
• Product developers
• Quality personnel