A scalable parallel algorithm for training a hierarchical mixture of neural experts

Parallel Computing

Volumn 28, Issue 6, 2002, Pages 861-891

  Estévez, Pablo A ^a   Paugam Moisy, Hélène ^b   Puzenat, Didier ^b,c   Ugarte, Manuel ^a  

^a UNIVERSITY OF CHILE   (Chile)

^b INSTITUT DES SCIENCES COGNITIVES   (France)

^c UNIVERSITÉ DES ANTILLES ET DE LA GUYANE   (France)

Author keywords

Artificial neural networks; Expectation maximization learning algorithm; Hierarchical mixture of experts; Parallel learning algorithms; Scalability

Indexed keywords

EXPERT SYSTEMS; HIERARCHICAL SYSTEMS; LEARNING ALGORITHMS; MULTILAYER NEURAL NETWORKS; PARALLEL ALGORITHMS;

PARALLEL LEARNING ALGORITHMS;

PARALLEL PROCESSING SYSTEMS;

EID: 0036601538     PISSN: 01678191     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8191(02)00078-9     Document Type: Article

References (40)

1. Improved learning algorithms for mixture of experts in multiclass classification
2. Implementations of multilayer neural networks on parallel architectures
3. Implementation of the self-organizing feature map on parallel computers
4. Maximum likelihood from incomplete data via the EM algorithm
5. Hierarchical mixture of experts and max-min propagation neural networks
6. Modular parallel implementation for HME neural networks
7. Mapping neural networks onto message-passing multicomputers
8. A computational study of the focus-of-attention EM-ML algorithm for PET reconstruction
9. Graph partitioning models for parallel computing
10. CuPit-2: A Portable parallel programming language for artificial neural networks
11. Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks
12. Adaptive mixture of experts
13. A Bayesian approach to model selection in hierarchical mixture of experts architectures
14. Hierarchical mixture of experts and the EM algorithm
15. A scalable parallel formulation of the backpropagation algorithm for hypercubes and related architectures
16. Forecasting electricity demand using nonlinear mixture of experts
17. Parallel image processing using neural networks: Applications in contrast enhancement of medical images
18. Transputers and neural networks: An analysis of implementation constraints and performance
19. Optimal speedup conditions for a parallel back-propagation algorithm
20. Parallel neural computing based on network duplicating
21. Multiprocessor simulation of neural networks
22. Neural networks: From massively parallel processing towards modular distributed processing
23. Parallel neural computation based on algebraic partitioning
24. Performance analysis of a pipelined back-propagation parallel algorithm
25. Exploiting domain-specific properties: Compiling parallel dynamic neural network algorithms into efficient code
26. Learning internal representations by error propagation
27. Mapping conjugate gradient algorithms for neutron diffusion: Applications onto SIMD, MIMD, and mixed-mode machines
28. Efficient mapping of backpropagation algorithm onto a network of workstations
29. Reducing the communication cost in simulating layered neural networks on a hypercube machine
30. Classification using hierarchical mixture of experts
31. Nonlinear prediction of acoustic vectors using hierarchical mixture of experts
32. Nonlinear gated experts for time series: Discovering regimes and avoiding overfitting