Neural networks are at the heart of AI—so ensure you’re on the cutting edge with this guide! For true beginners, get a crash course in Python and the mathematical concepts you’ll need to understand and create neural networks. Or jump right into programming your first neural network, from implementing the scikit-learn library to using the perceptron learning algorithm. Learn how to train your neural network, measure errors, make use of transfer learning, implement the CRISP-DM model, and more. Whether you’re interested in machine learning, gen AI, LLMs, deep learning, or all of the above, this is the AI book you need!
- Your practical introduction to programming neural networks
- Develop and train simple and multi-layer networks with Python
- Learn about algorithms, activation functions, transformers, and more
In this book, you'll learn about:
The Basics Learn about neural networks from the ground up! Understand how neural networks work and what their basic elements are, from algorithms and activation functions to transformers. Includes a primer on mathematics and Python for beginners!
Putting Theory into Practice Develop different types of neural networks: simple ones, multi-layer ones, and even deep neural networks. Walk through diverse practical examples, from image classification to large language models (LLMs).
Letting the Machine's Learn Train your newly created (or modified!) neural network. Get expert tips on skillfully using training data, selecting the right tools, increasing the hit rates of your models, and avoiding pitfalls.
Highlights include:
- Network creation
- Network training
- Supervised and unsupervised learning
- Reinforcement learning
- Algorithms
- Multi-layer networks
- Deep neural networks
- Back propagation
- Transformers
- Python
- Mathematical concepts
About the Author
Dr. Roland Schwaiger is a software developer, freelance trainer, and consultant. He has a PhD in mathematics and he has spent many years working as a researcher in the development of artificial neural networks, applying them in the field of image recognition. In his work, he places great importance on bridging the gap between theory and practice. Whether as an author, consultant, or lecturer, he is passionate about sharing his enthusiasm with others.
Dr. Joachim Steinwendner is a scientific project leader specializing in data science, machine learning, recommendation systems, and deep learning. He has been involved in the development of neural networks, guiding them from a cutting-edge research topic to their current everyday relevance, and has worked across variou
