Machine Learning and Deep Learning With Python: Use Python Jupyter to Implement Mathematical Concepts, Machine Learning Algorithms and Deep Learning Neural Networks
Über dieses E-Book
Starting with the basics of Python programming, this book gradually builds up to more advanced topics, such as artificial neural networks, convolutional neural networks, and generative adversarial networks. Each chapter is filled with clear explanations, practical examples, and step-by-step tutorials that allow readers to gain a deep understanding of the underlying principles of machine learning and deep learning.
Throughout the book, readers will also learn how to use popular Python libraries and packages, including numpy, pandas, scikit-learn, TensorFlow, and Keras, to build and train powerful machine learning and deep learning models for a variety of real-world applications, such as regression and classification, K-means, support vector machines, and recommender systems.
Whether you are a seasoned data scientist or a beginner looking to enter the world of machine learning, this book is the ultimate resource for mastering these cutting-edge technologies and taking your skills to the next level. High-school level of mathematical knowledge and all levels (including entry-level) of programming skills are good to start, all Python codes are available at Github.com.
Table Of Contents
1 Introduction
1.1 Artificial Intelligence, Machine Learning and Deep Learning
1.2 Whom This Book Is For
1.3 How This Book Is Organized
2 Environments
2.1 Source Codes for This Book
2.2 Cloud Environments
2.3 Docker Hosted on Local Machine
2.4 Install on Local Machines
2.5 Install Required Packages
3 Math Fundamentals
3.1 Linear Algebra
3.2 Calculus
3.3 Advanced Functions
4 Machine Learning
4.1 Linear Regression
4.2 Logistic Regression
4.3 Multinomial Logistic Regression
4.4 K-Means Clustering
4.5 Principal Component Analysis (PCA)
4.6 Support Vector Machine (SVM)
4.7 K-Nearest Neighbors
4.8 Anomaly Detection
4.9 Artificial Neural Network (ANN)
4.10 Convolutional Neural Network (CNN)
4.11 Recommendation System
4.12 Generative Adversarial Network
References
About the Author
Mehr entdecken
Autoren-Profil
James Chen, a highly accomplished IT professional with a solid academic background, holds a degree from Tsinghua University, one of China’s most prestigious universities, and has developed a deep understanding of computer science theory and practices. With his extensive technical background, James has played key roles in designing and developing cutting-edge software solutions for a variety of industries including technology, financial, healthcare, e-commerce, etc. He has been working with all aspects of system design and development and actively contributed as the lead implementer of complex multi-clients and multi-tiered systems such as web systems, traditional n-tiered systems, mobile applications, and mixed software/hardware systems. He has a talent for identifying key business problems and designing customized solutions that are both efficient and effective.
His wide-ranging technical interests led him to the emerging fields of computer vision and machine learning since 2016, James has a passion for artificial intelligence and has honed his skills in this area through a combination of academic study and practical experiences. He has developed an in-depth understanding of the latest tools and techniques in computer vision and machine learning and is always looking for new ways to apply this knowledge to real-world problems.
