Experience the power of machine learning by working on nine real-world projects
Key Features
- Grasp the core concepts of machine learning (ML)
- Find out how to use neural networks in ML projects
- Learn how to build real-world projects using supervised and unsupervised learning algorithms
Book Description
From self-driving cars to artificial intelligence (AI) bots, machine learning (ML) is slowly spreading its reach and making our devices smarter. If you have ever wanted to play a role in the future of technology development, then here is your chance to get started with ML. This course breaks the complex topics of ML into simple concepts that are easier to understand.
The course starts with an introduction to ML, explaining its applications in the real-world and how it is different from AI. Next, you will learn supervised and unsupervised algorithms and understand the role of neural networks in ML. Once you understand the ML algorithms, you will dive into building interesting projects to consolidate your learning. You will learn how to build a board game review prediction model, how to build a credit card fraud detection model, how to tokenize word and sentences using natural language processing), how to build an object recognition model, how to build an image quality improvement model, how to build a text classification model, how to build an image analysis model, and how to build a data compression model.
By the end of this course, you will have gained the skills to create real-world ML solutions.
All the recourses for this course are avialable at https://github.com/PacktPublishing/Projects-in-Machine-Learning-From-Beginner-to-Professional
What you will learn
- Detect credit card fraud by using probability densities
- Become familiar with the natural language processing methodology
- Use the Canadian Institute for Advanced Research-10 (CIFAR-10) object recognition dataset to implement a deep neural network
- Improve image quality using Super-Resolution Convolutional Neural Network (SRCNN)
- Solve a text classification task using multiple classification algorithms
- Use K-means clustering in an unsupervised algorithm
Who this book is for
If you want to understand machine learning (ML) algorithms and concepts to build effective ML solutions for the modern world, this course is for you. Basic Python skills and a good understanding of mathematics are needed to get started with this course.
