University of Cebu-Banilad Library

Contents: Chapter 1: Introduction to artificial neural networks and perceptrons — Chapter 2: Neurons and artificial neurons — Chapter 3: Perceptron learning algorithm — Chapter 4: Limitations of perceptron and multi-layer neural networks — Chapter 5: Activation functions — Chapter 6: Gradients descent — Chapter 7: Backpropagation algorithm — Chapter 8: Applications of neural networks.

""Deep Learning Demystified: A Step-by-Step Introduction to Neural Networks" is a comprehensive guide designed to make the world of artificial neural networks accessible and engaging. With a focus on simplicity and clarity, this book offers readers an easy-to-follow journey through the fascinating field of deep learning, without requiring an extensive background in mathematics or programming.

Ever since the concept of Artificial Intelligence (AI) emerged, humans have dreamed of creating machines that can think and communicate like us. This dream is now becoming a reality through the advancements in AI, particularly with machine learning and deep learning. At the core of these technologies are Artificial Neural Networks (ANNs), which mimic the structure and function of the human brain to process and learn from data.

In this book, you will embark on a journey that begins with the basics of neural networks and perceptrons, and gradually progresses to more advanced concepts and applications. Each chapter is meticulously crafted to build your understanding step-by-step, ensuring you grasp the foundational principles before moving on to complex topics.

Key Topics Covered:

Chapter 1: Introduction to Artificial Neural Networks and Perceptrons

Explore the dream of AI and understand the basic concepts of neural networks.
Chapter 2: Neurons and Artificial Neurons

Dive into the structure and function of biological neurons and their artificial counterparts.
Chapter 3: Perceptron Learning Algorithm

Learn about the learning process of neural networks with practical examples in Python.
Chapter 4: Limitations of Perceptron and Multi-Layer Neural Networks

Discover the limitations of single-layer perceptrons and the rise of multi-layer networks.
Chapter 5: Activation Functions

Understand the role of activation functions and their various types, including Sigmoid, ReLU, and more.
Chapter 6: Gradient Descent

Delve into the gradient descent algorithm, its mathematical foundation, and its application in training neural networks.
Chapter 7: Backpropagation Algorithm

Learn about the backpropagation algorithm, a critical component in the training of deep neural networks.
Chapter 8: Applications of Neural Networks

Explore real-world applications of neural networks in image recognition, speech recognition, and natural language processing.
Each chapter is rich with examples, illustrations, and practical insights, making complex topics understandable and enjoyable. Whether you are a student, a professional, or simply someone with a keen interest in AI, this book is your gateway to understanding and harnessing the power of neural networks.

Join Kilho Shin, an AI Engineer with a passion for teaching complex topics in an easy and engaging way, as he guides you through this exciting field. With a PhD from the University of Southern California, Kilho brings a wealth of knowledge and experience to this book, ensuring that you not only learn but also enjoy the process.

Embrace the future of AI with "Deep Learning Demystified" and start your journey towards mastering neural networks today." —Provided by the publisher

Adult

Purchased Ortega, Eric College of Computer Studies Computer Science

Text in English