An analytical framework for optimizing neural networks

Neural Networks

Volumn 6, Issue 1, 1993, Pages 79-97

  Gee, Andrew H ^a   Aiyer, Sreeram V B ^a   Prager, Richard W ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Combinatorial optimization; Eigenvector analysis; Hamilton paths; Hopfield network; Neurodynamics; Point matching; Problem mappings; Valid subspace

Indexed keywords

COMBINATORIAL MATHEMATICS; EIGENVALUES AND EIGENFUNCTIONS; LYAPUNOV METHODS; OPTIMIZATION; SYSTEM STABILITY;

COMBINATORIAL OPTIMIZATION; EIGENVECTOR ANALYSIS; HAMILTON PATHS; HOPFIELD NETWORK; NEURODYNAMICS; POINT MATCHING; PROBLEM MAPPINGS; VALID SUBSPACE;

NEURAL NETWORKS;

EID: 0027259668     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(05)80074-7     Document Type: Article

References (22)

1. Solving combinatorial optimization problems using neural networks
2. A Hopfield network implementation of the Viterbi algorithm for Hidden Markov Models
3. A theoretical investigation into the performance of the Hopfield model
4. Elastic matching and pattern recognition in neural networks
5. Competitive neural architecture for hardware solution to the assignment problem
6. Neural networks and combinatorial optimization problems—the key to a successful mapping
7. A subspace approach to invariant pattern recognition using Hopfield networks
8. Polyhedral combinatorics and neural networks
9. ‘Teachers and Classes’ with neural networks
10. Neurons with graded response have collective computational properties like those of two-state neurons
11. ‘Neural’ computation of decisions in optimization problems
12. On problem solving with Hopfield neural networks
13. Object recognition based on graph matching implemented by a Hopfield-style neural network
14. Neural network solution to the link scheduling problem using convex relaxation
15. Neural networks and NP-complete optimization problems: a performance study on the graph bisection problem
16. A new method for mapping optimization problems onto neural networks
17. Simple ‘neural’ optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit
18. Improving the performance of the Hopfield-Tank neural network through normalization and annealing
19. Graph partitioning using annealed neural networks
20. On the stability of the TSP problem algorithm of Hopfield and Tank