Introduction to Machine Learning
Overview
This course introduces participants to both supervised and unsupervised learning algorithms with discussion of what datasets lend themselves to solutions with the various ML techniques. Hands-on labs are designed to assist the learner in understanding the concepts and are all done using Jupyter Notebooks. Where necessary, background material in Linear Algebra, Probability, and Python will be presented.
Who Should Take This Course
Audience
This course is suitable for Mathematicians, Statisticians, Data Scientists, etc. who want to get a solid introduction to Machine Learning algorithms and methods.
Prerequisites
Students should have a basic understanding of Linear Algebra concepts such as vectors, Dot product, and matrices, basic Calculus understanding of derivatives and rate of change and fundamental Probability concepts such as bias and variance. Basic understanding of Python and pandas is helpful.
Course Outline
Introduction to Machine Learning
- Introduction to Machine Learning Concepts
- Introduction to Modeling
- How ML is different from direct modeling
- Types of ML Algorithms
- Supervised Learning
- Unsupervised Learning
- Explainable / Non-Explainable
- Supervised Learning Algorithms
- Classification
- Regression
- Model Assessment
- Projects
- Unsupervised Learning Algorithms
- Clustering
- Dimensionality Reduction
- Anomaly detection
- Model Assessment
- Projects
- Data Visualization
- Visualization Theory
- Visualization Libraries
- Projects
- Special Topics
- Reinforcement Learning
- Recommendations
- Sentiment Analysis
- Neural Networks
- Future Trends
- Hands-on Tools Used in Class
- Jupyter Notebooks / SageMaker Studio
- Pandas / Numpy
- Scikit-Learn
- Visualization Libraries (Matplotlib, Seaborn)
- Python packages Review
- Pandas
- Numpy
- Math Background (where necessary)
- Probability
- Linear Algebra
- Calculus