Artificial neural networks are useful tools for pattern recognition because they realize nonlinear mapping between input and output spaces. This ability is tuned by supervised learning methods such as back-propagation. In the supervised learning methods, desired outputs of the neural network are nee
โฆ LIBER โฆ
UNEQ: A class modelling supervised pattern recognition technique
โ Scribed by Derde, M. P. ;Massart, D. L.
- Book ID
- 105118065
- Publisher
- Springer-Verlag
- Year
- 1986
- Weight
- 673 KB
- Volume
- 89
- Category
- Article
- ISSN
- 0344-838X
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
A self-supervised learning system for pa
โ
K Yamauchi; M Oota; N Ishii
๐
Article
๐
1999
๐
Elsevier Science
๐
English
โ 1022 KB
Fuzzy techniques in pattern recognition:
โ
M.M. Gupta
๐
Article
๐
1984
๐
Elsevier Science
๐
English
โ 122 KB
In conclusion, this book left me with mixed feelings. It definitely gives a complete account of the application of the decentralized method for manipulator control and as such, I recommend it to every engineer or scientist with interest in robotics. However, I have many questions about the effective
A class-modelling technique based on pot
โ
Michele Forina; Carla Armanino; Riccardo Leardi; Giuliana Drava
๐
Article
๐
1991
๐
John Wiley and Sons
๐
English
โ 898 KB
Optimal linear feature selection for a g
โ
Dean M Young; Patrick L Odell; Virgil R Marco
๐
Article
๐
1985
๐
Elsevier Science
๐
English
โ 331 KB
A Class of Pattern-Forming Models
โ
P. C. Fife; M. Kowalczyk
๐
Article
๐
1999
๐
Springer
๐
English
โ 174 KB
Tool wear monitoring in turning using a
โ
H.V. Ravindra; Y.G. Srinivasa; R. Krishnamurthy
๐
Article
๐
1993
๐
Elsevier Science
๐
English
โ 436 KB