Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Simulation Modeling with Python

You're reading from   Hands-On Simulation Modeling with Python Develop simulation models to get accurate results and enhance decision-making processes

Arrow left icon
Product type Paperback
Published in Jul 2020
Publisher Packt
ISBN-13 9781838985097
Length 346 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Giuseppe Ciaburro Giuseppe Ciaburro
Author Profile Icon Giuseppe Ciaburro
Giuseppe Ciaburro
Arrow right icon
View More author details
Toc

Table of Contents (16) Chapters Close

Preface 1. Section 1: Getting Started with Numerical Simulation
2. Chapter 1: Introducing Simulation Models FREE CHAPTER 3. Chapter 2: Understanding Randomness and Random Numbers 4. Chapter 3: Probability and Data Generation Processes 5. Section 2: Simulation Modeling Algorithms and Techniques
6. Chapter 4: Exploring Monte Carlo Simulations 7. Chapter 5: Simulation-Based Markov Decision Processes 8. Chapter 6: Resampling Methods 9. Chapter 7: Using Simulation to Improve and Optimize Systems 10. Section 3: Real-World Applications
11. Chapter 8: Using Simulation Models for Financial Engineering 12. Chapter 9: Simulating Physical Phenomena Using Neural Networks 13. Chapter 10: Modeling and Simulation for Project Management 14. Chapter 11: What's Next? 15. Other Books You May Enjoy

Understanding feedforward neural networks

The processing from the input layer to the hidden layer(s) and then to the output layer is called feedforward propagation. The transfer function is applied at each hidden layer, and then the activation function value is propagated to the next layer. The next layer can be another hidden layer or the output layer.

Important note

The term "feedforward" is used to indicate the networks in which each node receives connections only from the lower layers. These networks emit a response for each input pattern but fail to capture the possible temporal structure of the input information or to exhibit endogenous temporal dynamics.

Exploring neural network training

The learning ability of an ANN is manifested in the training procedure. This represents the crucial phase of the whole algorithm as it is through the characteristics extracted during training that the network acquires the ability to generalize. The training takes place...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €18.99/month. Cancel anytime