To view this video please enable JavaScript.
Course Description
Machine learning is like teaching a computer to learn things on its own, just like a person learns new things. Imagine you have a robot friend and you want to teach it to distinguish between different fruits, such as apples and bananas. At first, you show the robot many pictures of apples and bananas and explain which one is which. The robot then looks at the pictures and tries to find things that are the same in all the apple pictures, and how they are different from the banana pictures. Machine learning teaches the robot to figure things out on its own by showing it many examples. It then learns from these examples and can make smart guesses even when it sees something that it’s never encountered before. Machine learning can be categorized into three main types based on the learning approach—we have supervised learning, unsupervised learning, and reinforcement learning in supervised learning. The robot is trained on a labeled data set where each example in the training data is associated with a target output. The goal is to learn a mapping from inputs to outputs, allowing the robot to make predictions or classifications on new unseen data.
In this KnowledgeCity course on Python for Data Science Advanced: Fundamentals of Machine Learning, you’ll learn about the fundamentals of machine learning, its history, and the different types. You’ll also learn about the machine learning process and data properties. Then we’ll cover some of Python's popular machine learning modules like SciKit, PyTorch, and TensorFlow.
What You'll Learn
- Identify the different types of machine learning, including supervised, unsupervised, and reinforcement learning
- Understand the history of machine learning
- Explain the machine learning process and data properties
- Distinguish how a labeled training data set maps inputs to target outputs for predictions and classifications
- Explore Python's popular machine learning modules including Scikit-learn, PyTorch, and TensorFlow
Key Takeaways
- Machine learning teaches a computer to learn from many examples and make smart guesses about data it has never encountered before.
- Machine learning can be categorized into three main types based on the learning approach: supervised learning, unsupervised learning, and reinforcement learning.
- In supervised learning, the model is trained on a labeled data set where each example is associated with a target output, learning a mapping from inputs to outputs.
- The course covers the fundamentals of machine learning, its history, the machine learning process, and data properties.
- Scikit-learn, PyTorch, and TensorFlow are popular Python modules for machine learning covered in this course.
Frequently Asked Questions
What will I learn in this course?
You'll learn about the fundamentals of machine learning, its history, and the different types, as well as the machine learning process and data properties. The course also covers popular Python machine learning modules like Scikit-learn, PyTorch, and TensorFlow.
What are the main types of machine learning covered?
The course covers three main types of machine learning based on the learning approach: supervised learning, unsupervised learning, and reinforcement learning.
Which Python machine learning libraries does this course cover?
It covers some of Python's popular machine learning modules, including Scikit-learn, PyTorch, and TensorFlow.
What skills does this course help build?
This course helps build skills in Data Interfaces, Machine Learning, Machine Learning Methods, and PyTorch (Machine Learning Library).
How is supervised learning explained in this course?
In supervised learning, the model is trained on a labeled data set where each example in the training data is associated with a target output, allowing it to learn a mapping from inputs to outputs and make predictions or classifications on new unseen data.
