Book Image

Python: Real-World Data Science

By : Fabrizio Romano, Dusty Phillips, Phuong Vo.T.H, Martin Czygan, Robert Layton, Sebastian Raschka
Book Image

Python: Real-World Data Science

By: Fabrizio Romano, Dusty Phillips, Phuong Vo.T.H, Martin Czygan, Robert Layton, Sebastian Raschka

Overview of this book

The Python: Real-World Data Science course will take you on a journey to become an efficient data science practitioner by thoroughly understanding the key concepts of Python. This learning path is divided into four modules and each module are a mini course in their own right, and as you complete each one, you’ll have gained key skills and be ready for the material in the next module. The course begins with getting your Python fundamentals nailed down. After getting familiar with Python core concepts, it’s time that you dive into the field of data science. In the second module, you'll learn how to perform data analysis using Python in a practical and example-driven way. The third module will teach you how to design and develop data mining applications using a variety of datasets, starting with basic classification and affinity analysis to more complex data types including text, images, and graphs. Machine learning and predictive analytics have become the most important approaches to uncover data gold mines. In the final module, we'll discuss the necessary details regarding machine learning concepts, offering intuitive yet informative explanations on how machine learning algorithms work, how to use them, and most importantly, how to avoid the common pitfalls.
Table of Contents (12 chapters)
Free Chapter
Table of Contents
Python: Real-World Data Science
Meet Your Course Guide
What's so cool about Data Science?
Course Structure
Course Journey
The Course Roadmap and Timeline

Chapter 11. Classifying Objects in Images Using Deep Learning

We used basic neural networks in Chapter 8, Beating CAPTCHAs with Neural Networks. A recent flood of research in the area has led to a number of significant advances to that base design. Today, research in neural networks is creating some of the most advanced and accurate classification algorithms in many areas.

These advances have come on the back of improvements in computational power, allowing us to train larger and more complex networks. However, the advances are much more than simply throwing more computational power at the problem. New algorithms and layer types have drastically improved performance, outside computational power.

In this chapter, we will look at determining what object is represented in an image. The pixel values will be used as input, and the neural network will then automatically find useful combinations of pixels to form higher-level features. These will then be used for the actual classification...