Transformations of sigma-pi nets: Obtaining reflected functions by reflecting weight matrices

Neural Networks

Volumn 15, Issue 3, 2002, Pages 375-393

  Neville, R S ^a   Eldridge, S ^a  

^a UNIVERSITY OF MANCHESTER   (United Kingdom)

Author keywords

Backpropagation; Neural networks; RAM nets; Reflection; Sigma pi; Transformation

Indexed keywords

FUNCTIONS; MAPPING; MATHEMATICAL TRANSFORMATIONS; REFLECTION;

NEURAL NETWORK WEIGHT MATRICES;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; ASSOCIATION; COMPUTER; INSTRUMENTATION; METHODOLOGY; PRIORITY JOURNAL; STANDARD; TASK PERFORMANCE; THEORY; WEIGHT MATRIX; NERVE CELL; PHYSIOLOGY;

NEURAL NETWORKS (COMPUTER); NEURONS;

EID: 0035989186     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(02)00023-0     Document Type: Article

References (45)

1. A review of RAM-based neural networks
2. Neural networks for solving systems of linear equations and related problems
3. Neural networks for solving systems of linear equations and related problems - Part II: Minimax and least absolute value problems
4. Learning probabilistic RAM nets using VLSI structures
5. Learning algorithms for RAM-based neural networks
6. Training strategies for probabilistic RAMs
7. Weighted nodes and RAM-nets: A unified approach
8. Training nets of hardware realisable sigma-pi units
9. Multilayer neural networks for solving a class of partial differential equations
10. An optimization network for matrix inversion
11. Artificial neural networks for solving ordinary and partial differential equations
12. Neural network approach to computing matrix inversion
13. The numerical solution of linear ordinary differential equations by feedforward neural networks
14. Annealing in RAM-based learning networks
15. RAM-based sigma-pi nets for high accuracy function mapping
16. Learning Boolean functions without training
17. Toward second-order generalisation
18. Adaptive associative reward-penalty algorithms for sigma-pi networks
19. Generalisation in sigma-pi networks
20. Adaptive critic for sigma-pi networks
21. Mapping sigma-pi networks and the associative reward-penalty training regime to the associative string processor
22. Partially pre-calculated weights for the backpropagation learning regime and high accuracy function mapping using continuous input RAM-based sigma-pi nets in neural networks
23. A neural network for computing eigenvectors and eigenvalues
24. Electronic realization of a recurrent neural network for solving simultaneous linear equations
25. A recurrent neural network for real-time matrix inversion
26. Solving simultaneous linear equations using recurrent neural networks
27. Structured trainable networks for matrix algebra
28. Three-dimensional structured networks for matrix equation solving
29. Parallel structured networks for solving a wide variety of matrix algebra problems
30. Recurrent neural networks for LU decomposition and Cholesky factorization
31. A multilayer recurrent neural network for solving continuous-time algebraic Riccati equations
32. A recurrent neural network for solving linear projection equations
33. Solving least squares problems by neural network approach, speech, image processing and neural networks, 1994