Because this book was written in the early 90s, the code examples are likely in C or Fortran, and the diagrams are monochrome. Here is how to get the most out of it today:
Modern AI books often skip Hopfield Networks because they aren't used in modern image recognition. However, Fu’s explanation of Hopfield networks is excellent for understanding Associative Memory (how a network can recall neural networks in computer intelligence limin fu pdf link
Limin Fu’s work is respected for its structured approach to different "schools" of neural networks. The book typically covers: Because this book was written in the early
"Neural Networks in Computer Intelligence" by Limin Fu is a foundational text that surveys neural network models, learning algorithms, and their applications within artificial intelligence and pattern recognition. The book emphasizes both theoretical underpinnings and practical implementations, covering network architectures, training methods, and examples across classification, clustering, and function approximation. Limin Fu’s work is respected for its structured
Use this book to understand "shallow" networks. Once you understand Backpropagation as explained by Fu, compare it to modern Deep Learning textbooks. You will realize that the core logic has not changed, only the scale (layers) and the computing power.
Google Books often has a preview of the text. While it may not allow you to download the full PDF, it allows you to read significant portions online.