How do the networks learn? The short-term knowledge in artificial neural networks (ANN) is stored in the states of neurons and their connections correspond to the long-term knowledge. In this connection, learning means the adaptation of weights or adding or removing connections between neurons. This divides networks to static and dynamic neural networks. In static
Welcome- Themes
- Introduction to forest-based bioeconomy
- Wood products
- Natural fibre products
- Man-made bio-based fibre products
- Bio-based nanomaterials
- Recycled fibre
- Pulping and biorefining
- Energy and biofuels
- Biomass chemistry and physiology
- Material testing and product properties
- Forests and other biomass resources
- Supply chain
- Process control and automation
- Asset management
- Business and investment planning
- Environmental control and management
- Learning paths
- Other resources
- Tools
- Contact
- Profile
How do the networks learn?
After reading this article you will..
- Understand the backpropagation as a learning principle.
Process control and automation
- Introduction to process control and automation
- Development of process automation
- Fibre process automation
- Chemical recovery as a control object
- Advances in paper machine automation
- Paper machine as a dynamical system
- Tasks in paper machine control and management
- Control of stock flow concentration and quality
- Machine direction control
- Cross-directional control – The static optimisation
- Cross-directional control – Dynamics
- Cross-directional control – further aspects
- Controlling functional paper properties
- Managing grade chances in the paper machine
- Managing disturbances caused by broke and recovered solids
- Millwide systems
- Modelling and control methods
Authors & references
Edited by:
Professor Emeritus Kauko Leiviskä, University of Oulu
Based on: Leiviskä, K., Methods (Chapter 3). In: Leiviskä, K. (ed), Process and Maintenance Management, (Book 14), Papermaking Science and Technology. 2nd edition. Jyväskylä, 2009, Paper Engineer’s Association/Paperi ja Puu Oy. pp. 28–71.
References:
- Wells, G. 1995. An introduction to neural networks. In: Boullart, L., Krijgsman, A., Vingerhoeds, R.A. (eds.): Applications of Artificial Intelligence in Process Control. Pergamon Press, New York.
Videos
Exercises
This page has been updated 25.11.2020
Privacy Overview
This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Our site uses functional cookies. Functional cookies are cookies that ensure the proper functioning of the Website (e.g. cookies for login or registration, language preferences) and their installation does not require your permission.
Read more.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.
3rd Party Cookies
This website uses Google Analytics and Facebook to collect anonymous information such as the number of visitors to the site, and the most popular pages.
Keeping this cookie enabled helps us to improve our website.
Please enable Strictly Necessary Cookies first so that we can save your preferences!