Book Image

Machine Learning for OpenCV - Advanced Methods and Deep Learning [Video]

By : Michael Beyeler
Book Image

Machine Learning for OpenCV - Advanced Methods and Deep Learning [Video]

By: Michael Beyeler

Overview of this book

<p>Computer vision is one of today's most exciting application fields of Machine Learning, From self-driving cars to medical diagnosis, computer vision has been widely used in various domains.</p> <p>This course will cover essential concepts such as classifiers and clustering and will also help you get acquainted with neural networks and Deep Learning to address real-world problems.</p> <p>All the code and supporting files for this course are available on Github at <a style="color: #fa8d11;" href="https://github.com/PacktPublishing/Machine-Learning-for-OpenCV-Advanced-Methods-and-Deep-Learning" target="blank">https://github.com/PacktPublishing/Machine-Learning-for-OpenCV-Advanced-Methods-and-Deep-Learning</a></p> <p>The course will also guide you through creating custom graphs and visualizations, and show you how to go from raw data to beautiful visualizations. By the end of this course, you will be ready to create your own ML system and will also be able to take on your own machine learning problems.</p> <h2>Style and Approach</h2> <p>This course walks you through the key elements of OpenCV and its powerful Machine Learning classes while demonstrating how to get to grips with a range of models.</p>

Related Content you might be interested in

Current Title:

Small book image
Machine Learning for OpenCV - Advanced Methods and Deep Learning [Video]
Michael Beyeler
May, 2018 | 2 hours 25 minutes
No titles found
Table of Contents (5 chapters)
Free Chapter
1
Implementing a Spam Filter with Bayesian Learning
The Course Overview
Understanding and Implementing Bayesian Classifier
Classifying Emails Using Naive Bayes Classifier
2
Discovering Hidden Structures with Unsupervised Learning
Understanding Unsupervised Learning and k-means Clustering
Understanding Expectation-Maximization
Compressing Color Spaces Using k-means
Classifying Handwritten Digits Using k-means
Organizing Clusters as a Hierarchical Tree
3
Using Deep Learning to Classify Handwritten Digits
Understanding and Implementing Perceptron
Understanding and Implementing Multilayer Perceptrons
Getting Acquainted with Deep Learning
Classifying Handwritten Digits
4
Combining Different Algorithms into an Ensemble
Understanding Ensemble Methods
Combining Decision Trees into a Random Forest
Using Random Forests for Face Recognition
Implementing AdaBoost
Combining Different Models into a Voting Classifier
5
Selecting the Right Model with Hyperparameter Tuning
Evaluating a Model
Understanding Cross-Validation
Estimating Robustness Using Bootstrapping
Assessing the Significance of Our Results
Tuning Hyperparameters with Grid Search
Chaining Algorithms Together to Form a Pipeline
Chapter 2
Discovering Hidden Structures with Unsupervised Learning
Content Locked
Section 4
Classifying Handwritten Digits Using k-means
Let's say our task is to classify handwritten digits. Don't most zeros look similar, if not the same? And don't all zeros look categorically different from all possible ones? Doesn't this mean we could use clustering for classification as well? Let's find out together. In this video, we will attempt to use k-means to try and classify handwritten digits. In other words, we will try to identify similar digits without using the original label information. element with a class. - Generate a labels vector to find out which images were grouped into which clusters - Create a confusion matrix
Previous Section
End of Section 4
Next Section