Overview
In this course, you'll learn how to apply Supervised, Unsupervised and Reinforcement Learning techniques for solving a range of data science problems.
Syllabus
- Introduction to Machine Learning
- Supervised Learning
- From theory to application, this course guides you through supervised learning essentials. Learn to select, implement, and refine models that solve complex classification and regression tasks.
- Introduction to Neural Networks with TensorFlow
- Learn the fundamentals of neural networks with Python and TensorFlow, and then use your new skills to create your own image classifier—an application that will first train a deep learning model on a dataset of images and then use the trained model to classify new images.
- Unsupervised Learning
- Learn to apply unsupervised learning methods like K-means and Gaussian mixtures to extract value from raw data. Develop skills in feature extraction and cluster validation to enhance data analysis.
- Congratulations!
- Congratulations on finishing your program!
- Prerequisite: Python for Data Analysis
- Prerequisite: SQL for Data Analysis
- Prerequisite: Command Line Essentials
- Prerequisite: Git & Github
- Additional Material: Python for Data Visualization
- Additional Material: Statistics for Data Analysis
- Additional Material: Linear Algebra
Taught by
Michael Littman and Charles Isbell
Reviews
4.4 rating, based on 7 Class Central reviews
Showing Class Central Sort
-
Superb course. At every step they probe how we should choose what to do next instead of just telling the steps.
-
Course Review: "Machine Learning Fundamentals" I recently started taking the course "Machine Learning Fundamentals," and so far, it has been an enriching and insightful learning experience. This course provides a comprehensive introduction to the p…
-
An excellent overview of the field. The lectors are great, and I particularly liked the cross-references and similarities between different topics that they show.
-
Poor delivery, outdated and barely an overview of machine learning algorithms. So watered down that there's very little meat (maths) left.
-
-
-