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
ATZ-Fachkongress

Chassis.tech plus 2024


4 Kongresse in einer Veranstaltung

Treffen Sie in München die Fachleute von Chassis, Lenkung, Bremsen sowie Reifen/Räder.
Erweiterte Suche
Anmelden
nach oben

2021 | Buch

AI Sculpture Kapitel lesen Erstes Kapitel lesen

An Intuitive Exploration of Artificial Intelligence

Theory and Applications of Deep Learning

verfasst von: Dr. Simant Dube

Verlag: Springer International Publishing

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

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book develops a conceptual understanding of Artificial Intelligence (AI), Deep Learning and Machine Learning in the truest sense of the word. It is an earnest endeavor to unravel what is happening at the algorithmic level, to grasp how applications are being built and to show the long adventurous road in the future.
An Intuitive Exploration of Artificial Intelligence offers insightful details on how AI works and solves problems in computer vision, natural language understanding, speech understanding, reinforcement learning and synthesis of new content. From the classic problem of recognizing cats and dogs, to building autonomous vehicles, to translating text into another language, to automatically converting speech into text and back to speech, to generating neural art, to playing games, and the author's own experience in building solutions in industry, this book is about explaining how exactly the myriad applications of AI flow out of its immense potential.
The book is intended to serve as a textbook for graduate and senior-level undergraduate courses in AI. Moreover, since the book provides a strong geometrical intuition about advanced mathematical foundations of AI, practitioners and researchers will equally benefit from the book.

Inhaltsverzeichnis

Frontmatter

Foundations

Frontmatter
Chapter 1. AI Sculpture
Abstract
Michelangelo could see an angel trapped in a block of marble ready to be sculpted out of it. Rodin knew what to chop off to turn a marble block into a deeply engrossed thinker.
Simant Dube
Chapter 2. Make Me Learn
Abstract
AI learns in a similar way. It faces a challenging and unknown landscape and the goal is to reach spots where the loss function is very low, just like the Colorado river valley. Unlike human hikers, it doesn’t have a path laid out and it has to discover it. This is exactly what learning is in ML. In this chapter, we get a glimpse of how it happens. It occurs because starting from an initial spot, an AI learning process takes baby steps towards its goal all guided by the data.
Simant Dube
Chapter 3. Images and Sequences
Abstract
Previous chapters have laid out the foundations of AI for us in terms of the overall training process. We have an insight into the expressive power of deep neural networks, for which we used FFN with several hidden layers of neurons which are fully connected. Before the dawn of AI, shallow FFNs with one hidden layer were used in the feature space by ML practitioners. However they don’t work well for images and sequences.
Simant Dube
Chapter 4. Why AI Works
Abstract
One of the comments on AI has been that we don’t really understand what’s going inside the black box of an AI model. What are all the hidden neurons doing when a CNN is recognizing a cat? How is an AI model able to generalize to unseen examples? Another persistent comment has been that we don’t really know what’s happening during the training process. What is the nature of this optimization landscape? Why doesn’t the training get stuck in a local minimum?
Simant Dube
Chapter 5. Novice to Maestro
Abstract
The same way a sculptor creates a piece of art, an AI/ML model approximates a manifold. AI/ML models differ in their abilities. Some perform very simple approximation and some can handle highly complex manifolds. Those which are simpler are said to have high bias. Those which are capable of complex approximations have less bias and many degrees. They can carve in flexible ways depending on the training data. They are said to have high variance.
Simant Dube
Chapter 6. Unleashing the Power of Generation
Abstract
If you are asked to paint a flower, you may ask many questions. “What type is it? How many petals? How many sepals? What is its size? What should be the color? Should it be bending at an angle?” What you are doing is that you are collecting the generative parameters of the flower. From these parameters, you will create a painting.
Simant Dube
Chapter 7. The Road Most Rewarded
Abstract
We all face critical decision-making stages in life. What major should I study? Who should I marry? What career should I pursue? Should I quit my job and launch a startup?
Simant Dube
Chapter 8. The Classical World
Abstract
The topic of this book is AI, which is rooted in classical ML. In order to understand AI better, it is important to revisit the classical techniques. This chapter will take you on a brief journey through the ideas and methods, which laid the foundations of ML. The fundamental difference from AI is that one is working in a carefully designed feature space.
Simant Dube

Applications

Frontmatter
Chapter 9. To See Is to Believe
Abstract
It has been said that humans learned to stand and walk upright in order to see things faraway in the plains of Africa. We are blessed with an amazing sense of sight which allows us to perceive what is happening around us. As all new parents know, a newborn baby starts noticing them and the world. We can segment out objects in our visual field, recognize them, and infer their attributes. We can detect motion and are able to predict what is likely going to happen next.
Simant Dube
Chapter 10. Read, Read, Read
Abstract
There is one thing which humans do which no other animal does.
Simant Dube
Chapter 11. Lend Me Your Ear
Abstract
Communication is key to human experience. Evolution enabled living things to pick up vibrations in air to make sense of what is happening around them and to proactively produce such vibrations in order to interact with others. Humans have taken this gift of sound recognition and synthesis to the next level by combining it with language and music, resulting in conversations, songs, symphonies, lectures, debates, and movie dialogues.
Simant Dube
Chapter 12. Create Your Shire and Rivendell
Abstract
One of the joys of Hollywood movies is stepping into worlds, dreamlike and fantastic. The Shire and Rivendell are magical works of art created by the human mind. Paintings, theater, movies, music, stories, poetry, and myths express the human mind’s innate desire to express itself. When we look at the cave paintings of Chauvet Cave, we need no further proof of the intelligence of their creators.
Simant Dube
Chapter 13. Math to Code to Petaflops
Abstract
AI is a great example of how rapid advances in software tools and hardware have synergized to create a revolution in computing. High-level tools which are built on others allow higher abstraction and quick experimentation, making it easy for AI engineers to forge ahead. The speed of execution of brilliant ideas matters.
Simant Dube
Chapter 14. AI and Business
Abstract
AI solves problems and improves the state of the art. It does so within an organizational context. Goals may include improvement of existing products and services or creation of altogether new ones. It may be just streamlining of current business operations by removing inefficiencies. Organizations can be in either the public or private sector, and the same principles of effective use of AI will apply to both.
Simant Dube

The Road Ahead

Frontmatter
Chapter 15. Keep Marching On
Abstract
In Chaps. 4 and 5, we learned the key reasons for the success of AI, which is its phenomenal expressive power, SGD not getting trapped in local minima, and ingeniously designed AI solutions trained with adequate data.
Simant Dube
Chapter 16. Benevolent AI for All
Abstract
Human history teaches us that there are two sides of human nature. The Strange Case of Dr. Jekyll and Mr. Hyde is in fact not strange. “All human beings, as we meet them, are commingled out of good and evil,” notes Robert Louis Stevenson, the perceptive author of the celebrated story. Individually we may believe that we are good, but collectively the two sides of our nature are very apparent. On the one side, we have public libraries and schools; on the other side, we have weapons of mass destruction.
Simant Dube
Chapter 17. Am I Looking at Myself?
Abstract
One of the direct, first-hand, and subjective experiences of our own intelligence we all have is when we say “Aha! I understand!” This phenomenal mental experience is referred as “qualia” by philosophers.
Simant Dube
Backmatter
Metadaten
Titel
An Intuitive Exploration of Artificial Intelligence
verfasst von
Dr. Simant Dube
Copyright-Jahr
2021
Electronic ISBN
978-3-030-68624-6
Print ISBN
978-3-030-68623-9
DOI
https://doi.org/10.1007/978-3-030-68624-6

Premium Partner

    Bildnachweise