Marcin Mazureknarzędzia online · artykuły · księgarniaRSS
Okładka: Simplified Machine Learning

Simplified Machine Learning

Autor: Dr. Pooja Sharma

Helionebook

98,10 zł 109,00 zł -10%

Kup w księgarni Helion

Czytaj fragmentPobierz PDF

Kategorie
Deep Learning, Machine Learning, PyTorch
Wydawca
BPB Publications
Rodzaj
ebook
Stron
266
Data wydania
2024-06-15
ISBN
9789355516145
Formaty
ePub (8,2MB) · Mobi (8,2MB)

Fragment książki — 21 stron

Kliknij stronę, żeby powiększyć. Całość możesz przeczytać online albo pobrać jako PDF. Fragment udostępniony przez wydawcę.

  • Fragment „Simplified Machine Learning” — strona 1 z 211
  • Fragment „Simplified Machine Learning” — strona 2 z 212
  • Fragment „Simplified Machine Learning” — strona 3 z 213
  • Fragment „Simplified Machine Learning” — strona 4 z 214
  • Fragment „Simplified Machine Learning” — strona 5 z 215
  • Fragment „Simplified Machine Learning” — strona 6 z 216
  • Fragment „Simplified Machine Learning” — strona 7 z 217
  • Fragment „Simplified Machine Learning” — strona 8 z 218
  • Fragment „Simplified Machine Learning” — strona 9 z 219
  • Fragment „Simplified Machine Learning” — strona 10 z 2110
  • Fragment „Simplified Machine Learning” — strona 11 z 2111
  • Fragment „Simplified Machine Learning” — strona 12 z 2112
  • Fragment „Simplified Machine Learning” — strona 13 z 2113
  • Fragment „Simplified Machine Learning” — strona 14 z 2114
  • Fragment „Simplified Machine Learning” — strona 15 z 2115
  • Fragment „Simplified Machine Learning” — strona 16 z 2116
  • Fragment „Simplified Machine Learning” — strona 17 z 2117
  • Fragment „Simplified Machine Learning” — strona 18 z 2118
  • Fragment „Simplified Machine Learning” — strona 19 z 2119
  • Fragment „Simplified Machine Learning” — strona 20 z 2120
  • Fragment „Simplified Machine Learning” — strona 21 z 2121

Opis

Explore the world of Artificial Intelligence with a deep understanding of Machine Learning concepts and algorithms

Key Features
A detailed study of mathematical concepts, Machine Learning concepts, and techniques.
Discusses methods for evaluating model performances and interpreting results.
Explores all types of Machine Learning (supervised, unsupervised, reinforcement, association rule mining, artificial neural network) in detail.
Comprises numerous review questions and programming exercises at the end of every chapter.

Description
"Simplified Machine Learning" is a comprehensive guide that navigates readers through the intricate landscape of Machine Learning, offering a balanced blend of theory, algorithms, and practical applications.

The first section introduces foundational concepts such as supervised and unsupervised learning, regression, classification, clustering, and feature engineering, providing a solid base in Machine Learning theory. The second section explores algorithms like decision trees, support vector machines, and neural networks, explaining their functions, strengths, and limitations, with a special focus on deep learning, reinforcement learning, and ensemble methods. The book also covers essential topics like model evaluation, hyperparameter tuning, and model interpretability. The final section transitions from theory to practice, equipping readers with hands-on experience in deploying models, building scalable systems, and understanding ethical considerations.

By the end, readers will be able to leverage Machine Learning effectively in their respective fields, armed with practical skills and a strategic approach to problem-solving.

What you will learn
Solid foundation in Machine Learning principles, algorithms, and methodologies.
Implementation of Machine Learning models using popular libraries like NumPy, Pandas, PyTorch, or scikit-learn.
Knowledge about selecting appropriate models, evaluating their performance, and tuning hyperparameters.
Techniques to pre-process and engineer features for Machine Learning models.
To frame real-world problems as Machine Learning tasks and apply appropriate techniques to solve them.

Who this book is for
This book is designed for a diverse audience interested in Machine Learning, a core branch of Artificial Intelligence. Its intellectual coverage will benefit students, programmers, researchers, educators, AI enthusiasts, software engineers, and data scientists.

Table of Contents
1. Introduction to Machine Learning
2. Data Pre-processing
3. Supervised Learning: Regression
4. Supervised Learning: Classification
5. Unsupervised Learning: Clustering
6. Dimensionality Reduction and Feature Selection
7. Association Rule Mining
8. Artificial Neural Network
9. Reinforcement Learning
10. Project
Appendix
Bibliography

Linki do księgarni są linkami partnerskimi Grupy Helion i Księgarni PWN (przez sieć Adtraction). Ceny i dostępność pochodzą z oferty wydawcy i mogą się zmienić.