Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben

2024 | Buch

An Overview of Machine Learning Kapitel lesen Erstes Kapitel lesen

MATLAB Machine Learning Recipes

A Problem-Solution Approach

verfasst von: Michael Paluszek, Stephanie Thomas

Verlag: Apress

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

Harness the power of MATLAB to resolve a wide range of machine learning challenges. This new and updated third edition provides examples of technologies critical to machine learning. Each example solves a real-world problem, and all code provided is executable. You can easily look up a particular problem and follow the steps in the solution.
This book has something for everyone interested in machine learning. It also has material that will allow those with an interest in other technology areas to see how machine learning and MATLAB can help them solve problems in their areas of expertise. The chapter on data representation and MATLAB graphics includes new data types and additional graphics. Chapters on fuzzy logic, simple neural nets, and autonomous driving have new examples added. And there is a new chapter on spacecraft attitude determination using neural nets. Authors Michael Paluszek and Stephanie Thomas show how all of these technologies allow you to build sophisticated applications to solve problems with pattern recognition, autonomous driving, expert systems, and much more.
What You Will LearnWrite code for machine learning, adaptive control, and estimation using MATLABUse MATLAB graphics and visualization tools for machine learningBecome familiar with neural netsBuild expert systemsUnderstand adaptive controlGain knowledge of Kalman Filters
Who This Book Is For
Software engineers, control engineers, university faculty, undergraduate and graduate students, hobbyists.

Inhaltsverzeichnis

Frontmatter
Chapter 1. An Overview of Machine Learning
Abstract
Machine Learning is a field in computer science where data is used to predict, or respond to, future data. It is closely related to the fields of pattern recognition, computational statistics, and artificial intelligence. The data may be historical or updated in real time. Machine learning is important in areas like facial recognition, spam filtering, content generation, and other areas where it is not feasible, or even possible, to write algorithms to perform a task.
Michael Paluszek, Stephanie Thomas
Chapter 2. Data for Machine Learning in MATLAB
Abstract
By default, all variables in MATLAB are double-precision matrices. You do not need to declare a type for these variables. Matrices can be multidimensional and are accessed using one-based indices via parentheses.
Michael Paluszek, Stephanie Thomas
Chapter 3. MATLAB Graphics
Abstract
One of the issues with machine learning is understanding the algorithms and why an algorithm made a particular decision. In addition, you want to be able to easily understand the decision. MATLAB has extensive graphics facilities that can be harnessed for that purpose. Plotting is used extensively in machine learning problems. MATLAB plots can be two- or three-dimensional. MATLAB also has many plot types such as line plots, bar charts, and pie charts. Different types of plots are better at conveying particular types of data. MATLAB also has extensive surface and contour plotting capabilities that can be used to display complex data in an easy-to-grasp fashion. Another facility is 3D modeling. You can draw animated objects, such as robots or automobiles. These are particularly valuable when your machine learning involves simulations.
Michael Paluszek, Stephanie Thomas
Chapter 4. Kalman Filters
Abstract
Understanding or controlling a physical system often requires a model of the system, that is, knowledge of the characteristics and structure of the system. A model can be a predefined structure or can be determined solely through data. In the case of Kalman Filtering, we create a model and use the model as a framework for learning about the state of the system.
Michael Paluszek, Stephanie Thomas
Chapter 5. Adaptive Control
Abstract
Control systems need to react to the environment in a predictable and repeatable fashion. Control systems take measurements and use them to control the process. For example, a ship measures its heading and changes its rudder angle to attain a desired heading.
Michael Paluszek, Stephanie Thomas
Chapter 6. Fuzzy Logic
Abstract
Fuzzy logic [30] is an alternative approach to control system design. Fuzzy logic works within the framework of set theory and is better at dealing with ambiguities. For example, three sets might be defined for a sensor: hard failure, soft failure, and no failure. The three sets might overlap, and at any given time, the sensor may have a degree of membership in each set. In effect, you would be applying a degree of fuzziness.
Michael Paluszek, Stephanie Thomas
Chapter 7. Neural Aircraft Control
Abstract
Longitudinal control is the control about the pitch axis of an aircraft, it needs to work at all altitudes and speeds. In this chapter, we will implement a neural net to produce the critical parameters for a nonlinear aircraft control system. This is an example of online learning and applies techniques from multiple previous chapters.
Michael Paluszek, Stephanie Thomas
Chapter 8. Introduction to Neural Nets
Abstract
Neural networks, or neural nets, are a popular way of implementing machine “intelligence.” The idea is that they behave like the neuron in a brain. In our taxonomy, neural nets fall in the category of true machine learning, as shown on the right.
Michael Paluszek, Stephanie Thomas
Chapter 9. Classification of Numbers Using Neural Networks
Abstract
Pattern recognition in images is a classic application of neural nets. This chapter builds upon the previous one by exploring multilayer networks, which fall into the Machine Learning branch of our Autonomous Learning taxonomy. In this case, we will look at images of computer-generated digits and the problem of identifying the digits correctly. These images will represent numbers from scanned documents. Attempting to capture the variation in digits with algorithmic rules, considering fonts and other factors, quickly becomes impossibly complex, but with a large number of examples, a neural net can readily perform the task. We allow the weights in the net to perform the job of inferring rules about how each digit may be shaped, rather than codifying them explicitly.
Michael Paluszek, Stephanie Thomas
Chapter 10. Data Classification with Decision Trees
Abstract
In this chapter, we will develop the theory for binary decision trees. Decision trees can be used to classify data and fall into the Learning category in our Autonomous Learning taxonomy. Binary trees are easiest to implement because each node branches to two other nodes, or none. We will create functions for the decision trees and to generate sets of data to classify. Figure 10.1 shows a simple binary tree. Point “a” is in the upper-left quadrant. The first binary test finds that its x value is greater than one.
Michael Paluszek, Stephanie Thomas
Chapter 11. Pattern Recognition with Deep Learning
Abstract
Neural nets fall into the Learning category of our taxonomy. In this chapter, we will expand our neural net toolbox with convolution and pooling layers. A general neural net is shown in Figure 11.1. This is a “deep learning” neural net because it has multiple internal layers. Each layer may have a distinct function and form. In the previous chapter, our network had multiple layers, but they were all functionally similar and fully connected. In this chapter, we will also introduce another convolutional neural network.
Michael Paluszek, Stephanie Thomas
Chapter 12. Multiple Hypothesis Testing
Abstract
Tracking is the process of determining the position of other objects as their position changes with time. Air traffic control radar systems are used to track aircraft. Aircraft in flight must track all nearby objects to avoid collisions and to determine if they are threats. Automobiles with radar cruise control use their radar to track cars in front of them so that the car can maintain safe spacing and avoid a collision.
Michael Paluszek, Stephanie Thomas
Chapter 13. Autonomous Driving with MHT
Abstract
In this chapter, we will apply the MHT techniques from the previous chapter to the interesting problem of autonomous driving. As with MHT, this chapter falls in the Learning portion of our taxonomy. Consider a primary car that is driving along a highway at variable speeds. It carries a radar that measures the azimuth, range, and range rate. Cars pass the primary car, some of which change lanes from behind the car and cut in front. The multiple hypothesis system tracks all cars around the primary car.
Michael Paluszek, Stephanie Thomas
Chapter 14. Spacecraft Attitude Determination
Abstract
Many spacecraft use star cameras to determine their orientation. A star camera takes an image of the star field. The first step is to determine what in the image is a star. Bright areas in the image are aggregated into “blobs” that are assumed to be stars. A star camera usually is slightly defocused so that a star image is smeared over multiple pixels. The next step is to find the centroid of each blob. Once this is done, the patterns seen in the image can be compared with the image created by an onboard star catalog.
Michael Paluszek, Stephanie Thomas
Chapter 15. Case-Based Expert Systems
Abstract
In this chapter we will introduce case-based expert systems, an example of the artificial intelligence branch of our Autonomous Learning taxonomy. There are two broad classes of expert systems, rule-based and case-based. Rule-based systems have a set of rules that are applied to come to a decision; they are just a more organized way of writing decision statements in computer code.
Michael Paluszek, Stephanie Thomas
Backmatter
Metadaten
Titel
MATLAB Machine Learning Recipes
verfasst von
Michael Paluszek
Stephanie Thomas
Copyright-Jahr
2024
Verlag
Apress
Electronic ISBN
978-1-4842-9846-6
Print ISBN
978-1-4842-9845-9
DOI
https://doi.org/10.1007/978-1-4842-9846-6

Premium Partner

    Bildnachweise