About the course
Get hands-on with machine learning using Python.
Given the constantly increasing amounts of data they're faced with, programmers have to come up with better solutions to make machines smarter and reduce manual work. In this Machine Learning course, you'll use Python to craft better solutions and process them effectively.
We start by focusing on key ML algorithms and how they can be trained for classification and regression. We will also work with Supervised and Unsupervised learning to help to get to grips with both types of algorithm. We will use the highly popular Scikit-learn library throughout the course while performing various ML tasks.
By the end of the course, you will be adept at using the concepts and algorithms involved in Machine Learning. This is a highly practical course and will equip you with sufficient hands-on training to help you implement ML skills right after finishing the course.
All the code and supporting files for this course are available on Github at https://github.com/PacktPublishing/Learn-Machine-Learning-in-3-Hours
Style and Approach
This course consists of a series of worked example problems; for each worked example problem, we make use of different supervised and unsupervised Machine Learning algorithms. We also look at some smaller one-video worked examples to define a series of fundamental concepts which are crucial for reliably deploying stable Machine Learning systems in the real world.
What You Will Learn
- How Machine Learning algorithms fit data.
- Using PCA (Principal Component Analysis) to explore and visualize data easily.
- Implementing Unsupervised K-Means clustering.
- Leveraging the power of Unsupervised K-Nearest-Neighbor clustering.
- Effective implementation of Supervised SVM (Support Vector Machine) fitting
- Getting hands-on with Supervised Random Forest Fitting
- Implementing Supervised Gradient Boosting for classification
- Hyperparameter fitting and performance-tuning algorithms.
After taking a Physics degree at Oxford, Thomas Snell entered the Biophysics industry. Performing numerical simulation; from there, took a numerical simulation PhD in Geophysics. During his PhD, Thomas developed a keen interest in Machine Learning, eventually founding two open source projects: a cryptocurrency trader and an evolutionary system to design quantum algorithms. Shortly after sharing these projects with the open source community, he worked as a Data Scientist while finishing his PhD, developing a system to cluster job data and predict career paths for groups of individuals.
Dive into Core of Selenium Automation [Video]