Abbildung von: Machine Learning Theory and Applications - Wiley

Machine Learning Theory and Applications

Hands-on Use Cases with Python on Classical and Quantum Machines
Xavier Vasques(Autor*in)
Wiley (Verlag)
1. Auflage
Erschienen am 11. Januar 2024
512 Seiten
E-Book
ePUB mit Adobe-DRM
978-1-394-22062-5 (ISBN)
74,99 €inkl. 7% MwSt.
Systemvoraussetzungen
für ePUB mit Adobe-DRM
E-Book Einzellizenz
Als Download verfügbar
Machine Learning Theory and Applications

Enables readers to understand mathematical concepts behind data engineering and machine learning algorithms and apply them using open-source Python libraries

Machine Learning Theory and Applications delves into the realm of machine learning and deep learning, exploring their practical applications by comprehending mathematical concepts and implementing them in real-world scenarios using Python and renowned open-source libraries. This comprehensive guide covers a wide range of topics, including data preparation, feature engineering techniques, commonly utilized machine learning algorithms like support vector machines and neural networks, as well as generative AI and foundation models. To facilitate the creation of machine learning pipelines, a dedicated open-source framework named hephAIstos has been developed exclusively for this book. Moreover, the text explores the fascinating domain of quantum machine learning and offers insights on executing machine learning applications across diverse hardware technologies such as CPUs, GPUs, and QPUs. Finally, the book explains how to deploy trained models through containerized applications using Kubernetes and OpenShift, as well as their integration through machine learning operations (MLOps).

Additional topics covered in Machine Learning Theory and Applications include:

* Current use cases of AI, including making predictions, recognizing images and speech, performing medical diagnoses, creating intelligent supply chains, natural language processing, and much more

* Classical and quantum machine learning algorithms such as quantum-enhanced Support Vector Machines (QSVMs), QSVM multiclass classification, quantum neural networks, and quantum generative adversarial networks (qGANs)

* Different ways to manipulate data, such as handling missing data, analyzing categorical data, or processing time-related data

* Feature rescaling, extraction, and selection, and how to put your trained models to life and production through containerized applications

Machine Learning Theory and Applications is an essential resource for data scientists, engineers, and IT specialists and architects, as well as students in computer science, mathematics, and bioinformatics. The reader is expected to understand basic Python programming and libraries such as NumPy or Pandas and basic mathematical concepts, especially linear algebra.
Xavier Vasques, PhD, is the Chief Technology Officer of IBM Technology (France) and Distinguished Data Scientist at IBM. He currently holds the chair of cognitive sciences and technologies at the École National Supérieure de Cognitique located in the University of Bordeaux, France and he is member of the scientific council of the École des Mines d'Alès, France. He is a mathematician and head of the Clinical Neuroscience Research Laboratory based in Montpellier (France).

General Introduction


The Birth of the Artificial Intelligence Concept


Thomas Hobbes begins his Leviathan by saying, "Reason is nothing but reckoning." This aphorism implies that we could behave like machines. The film The Matrix, meanwhile, lets us imagine that we are controlled by an artificial creature in silico. This machine projects into our brains an imaginary, fictional world that we believe to be real. We are therefore deceived by calculations and an electrode piercing the back of our skull. The scenarios abound in our imagination. Fiction suggests to us that one day, it will be easy to replicate our brains, like simple machines, and far from the complexity that we currently imagine. Any mainstream conference on artificial intelligence (AI) routinely shows an image from The Terminator or 2001: A Space Odyssey.

If "reason is nothing but reckoning," we could find a mathematical equation that simulates our thinking, our consciousness, and our unconsciousness. This thought is not new. Since the dawn of time, humans have constantly sought to reproduce nature. The question of thought, as such, is one of the great questions that humanity has asked itself. What makes Odysseus able to get away with tricks, flair, imagination, and intuition? How do we reflect, reason, argue, demonstrate, predict, invent, adapt, make analogies, induce, deduce, or understand? Is there a model that allows us to approach these things? Throughout our history, we have claimed that a machine cannot calculate like humans or speak, debate, or multitask like humans. Our desire for mechanization over millennia has shown us that machines, tools, and techniques can accomplish these tasks that we had thought were purely human. Does this mean that machines have surpassed humans? We can only acquiesce to a wide range of tasks. Are machines human? No!

Since our species emerged, we have continued to create tools intended to improve our daily lives, increase our comfort, make our tasks less painful, protect us against predators, and discover our world and beyond. These same tools have also turned against us, even though they had not been endowed with any intelligence. Beyond the use as a tool of AI, the quest for the thinking machine can be viewed in a slightly different way. It can be seen as a desire to know who we are, or what we are. It can also be considered as a desire to play God. Since ancient times, philosophers and scientists have been asking these questions and trying to understand and imitate nature in the hope of giving meaning to our being and sometimes to gain control. This imitation involves the creation of simple or complex models more or less approaching reality. So it is with the history of AI. AI comes not only from the history of the evolution of human thought on the body and the nature of the mind through philosophy, myths, or science but also from the technologies that have accompanied us throughout our history, from the pebble used to break shells to the supercolliders used to investigate quantum mechanics. Some historians have found ancient evidence of human interest in artificial creatures, particularly in ancient Egypt, millennia before the coming of Jesus Christ (BCE). Articulated statues, which could be described as automatons, were used during religious ceremonies to depict a tradesperson such as a kneading baker or to represent Anubis or Qebehsenouf as a dog's head with movable jaws. Even if they are only toys or animated statuettes using screws, levers, or pulleys, we can see a desire to artificially reproduce humans in action. These objects are not capable of moving on their own, but imagination can help. Automatons may become a symbol of our progress and emancipatory promises. These advances have also been an opportunity for humans to question their own humanity. The use of AI has been the subject of many questions and sources of concern about the future of the human species and its dehumanization.

In Greek mythology, robot servants made by the divine blacksmith Hephaestus lay the foundations for this quest for artificial creation. Despite the fact that Hephaestus is a god with deformed, twisted, crippled feet, this master of fire is considered an exceptional craftsman who has created magnificent divine works. A peculiarity of the blacksmith, recounted in the Iliad, is his ability to create and animate objects capable of moving on their own and imitating life. He is credited with creating golden servants who assist him in his work and many other automatons with different functions, including guard dogs to protect the palace of Alkinoos, horses for the chariot of the Cabires, or the giant Talos to guard the island of Crete. Items crafted by Hephaestus are also clever, allowing the gates of Olympus to open on their own or the bellows of the forge to work autonomously. The materials such as gold and bronze used to make these artificial creatures offer them immense resistance and even immortality. These automatons are there to serve the gods and to perform tedious, repetitive, and daunting tasks to perfection by surpassing mortals. No one can escape the dog forged by Hephaestus, and no one can circumnavigate Crete three times a day as Talos does. The human dream may have found its origins here. In the time of Kronos, humans lived with the gods and led a life without suffering, without pain, and without work, because nature produced abundantly without effort. All you had to do was stretch out your arm to pick up the fruit. The young golden servants "perfectly embody the wealth, the beauty, the strength, the vitality of this bygone golden age for humans" (J.W. Alexandre Marcinkowski). This perfect world, without slavery, without thankless tasks, where humans do not experience fatigue and can dedicate themselves to noble causes, was taken up by certain philosophers including Aristotle, who in a famous passage from Politics sees in artificial creatures an advantage that is certain:

If every tool, when ordered, or even of its own accord, could do the work that benefits it. then there would be no need either of apprentices for the master workers or of slaves for the lords.

Aristotle, Politics

We can see in this citation one of the first definitions of AI. Hephaestus does not imitate the living but rather creates it, which is different from imitation. Blacksmith automatons have intelligence, voice, and strength. His creations do not equal the gods, who are immortal and impossible to equal. This difference shows a hierarchy between the gods and those living automatons who are their subordinates. The latter are also superior to humans when considering the perfection of the tasks that are performed simply, without defects or deception. This superiority is not entirely accurate in the sense that some humans have shown themselves to be more intelligent than automatons to achieve their ends. We can cite Medea's overcoming of Talos. Hephaestus is the only deity capable of creating these wondrous creatures. But these myths lay the foundations of the relationship between humans and technology. Hephaestus is inspired by nature, living beings, and the world. He makes models that do not threaten the mortal world. These creatures are even prehumans if we think of Pandora. In the Hellenistic period, machines were created, thanks to scientists and engineers such as Philo of Byzantium or Heron of Alexandria. We have seen the appearance of automatic doors that open by themselves at the sound of a trumpet, an automatic water dispenser, and a machine using the contraction of air or its rarefaction to operate a clock. Many automatons are also described in the Pneumatika and Automaton-Making by Héron. These automatons amaze but are not considered to produce things industrially and have no economic or societal impact; these machines make shows. At that time, there was likely no doubt that we could perhaps imitate nature and provide the illusion but surely not match it, unlike Hephaestus who instead competes with nature. The works of Hephaestus are perfect, immortal, and capable of "engendering offspring." When his creatures leave Olympus and join humans, they degenerate and die. Hephaestus, unlike humans, does not imitate the living but instead manufactures it. Despite thousands of years of stories, myths, attempts, and discoveries, we are still far from Hephaestus.

Nevertheless, our understanding has evolved. We have known for a century that our brain runs on fuel, oxygen, and glucose. It also works with electricity since neurons transmit what they have to transmit, thanks to electrical phenomena, using what are called action potentials. Electricity is something we can model. In his time, Galileo said that "nature is a book written in mathematical language." So, can we seriously consider the creation of a human brain, thanks to mathematics? To imagine programming or simulating thought, you must first understand it, take it apart, and break it down. To encode a reasoning process, you must first be able to decode it. The analysis of this process, or the desire for analysis in any case, has existed for a very long time.

The concepts of modern computing have their origins in a time when mathematics and logic were two unrelated subjects. Logic was notably developed, thanks to two philosophers, Plato and Aristotle. We do not necessarily make the connection, but without Plato, Aristotle, or Galileo, we might not have seen IBM, Microsoft, Amazon, or Google. Mathematics and logic are the basis of computer science. When AI began to develop, it was assumed that the functioning of thought could be mechanized. The study of the mechanization of thought or reasoning has a...

Dateiformat: ePUB
Kopierschutz: Adobe-DRM (Digital Rights Management)

Systemvoraussetzungen:

  • Computer (Windows; MacOS X; Linux): Installieren Sie bereits vor dem Download die kostenlose Software Adobe Digital Editions (siehe E-Book Hilfe).
  • Tablet/Smartphone (Android; iOS): Installieren Sie bereits vor dem Download die kostenlose App Adobe Digital Editions oder die App PocketBook (siehe E-Book Hilfe).
  • E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nicht Kindle)

Das Dateiformat ePUB ist sehr gut für Romane und Sachbücher geeignet – also für „fließenden” Text ohne komplexes Layout. Bei E-Readern oder Smartphones passt sich der Zeilen- und Seitenumbruch automatisch den kleinen Displays an.
Mit Adobe-DRM wird hier ein „harter” Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.

Bitte beachten Sie: Wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!

Weitere Informationen finden Sie in unserer  E-Book Hilfe.