Learning a large number of simple local concepts is both faster and easier than learning a single global concept. Inspired by this principle of divide and conquer, a number of modular learning approaches have been proposed by the computational intelligence community. In modular learning, the classification/regression/clustering problem is first decomposed into a number of simpler subproblems, a module is learned for each of these subproblems, and finally their results are integrated by a suitable combining method. Mixtures of experts and clustering are two of the techniques that are describable in this paradigm. In this paper we present a broad framework for Generalized Associative Modular Learning Systems (GAMLS). Modularity is introduced through soft association of each training pattern with every module. The coupled problems of learning the module parameters and learning associations are solved iteratively using deterministic annealing. Starting at a high temperature with only one modu...
|
3316
|
Neural Networks for Pattern Recognition
– Bishop
- 1995
|
|
570
|
Adaptive mixtures of local experts
– Jacobs, Jordan, et al.
- 1991
|
|
307
|
Locally weighted learning
– Atkeson, Moore, et al.
- 1997
|
|
221
|
Learning Bayesian Networks
– Heckerman, Geiger, et al.
- 1994
|
|
159
|
Classification by pairwise coupling
– Hastie, Tibshirani
- 1998
|
|
108
|
Statistical Mechanics and Phase Transitions in Clustering
– Rose, Gurewitz, et al.
- 1990
|
|
94
|
Optimal Linear Combinations of Neural Networks
– Hashem
- 1993
|
|
86
|
Local learning algorithms
– Bottou, Vapnik
- 1992
|
|
86
|
An experimental and theoretical comparison of model selection methods
– Kearns, Mansour, et al.
- 1997
|
|
63
|
The Distance-Weighted k-Nearest-Neighbor Rule
– Dudani
- 1976
|
|
62
|
G.: A deterministic annealing approach to clustering
– Rose, Gurewwitz, et al.
- 1990
|
|
54
|
An overview of predictive learning and function approximation
– Friedman
- 1994
|
|
50
|
Multiple Model Approaches to Modelling and Control. Taylor&Francis
– Murray-Smith, Johansen
- 1997
|
|
48
|
Self-learning fuzzy controller based on temporal back-propagation
– Jang, Sun
- 1992
|
|
42
|
Design and evolution of modular neural network architectures
– Happel, Murre
- 1994
|
|
35
|
A bayesian/information theoretic model of learning to learn via multiple task sampling
– Baxter
- 1997
|
|
32
|
Task Decomposition and Module Combination Based on Class Relations: A Modular Neural Network for Pattern Classification
– Lu, Ito
- 1999
|
|
25
|
On the Optimality of the Simple Bayesian Classi under Zero{One Loss
– Domingos, Pazzani
- 1997
|
|
23
|
A simplified neural network solution through problem decomposition: The case of Truck backer-upper
– Jenkins, Yuhas
- 1993
|
|
18
|
Adaptive fuzzy c-shells clustering and detection of ellipses
– Dave, Bhaswan
- 1992
|
|
17
|
Fuzzy multi-layer perceptron, inferencing and rule generation
– Mitra, Pal
- 1995
|
|
14
|
Structurally Adaptive Modular Networks for Non-Stationary Environments
– Ramamurti, Ghosh
- 1999
|
|
13
|
Scale-based clustering using the radial basis function network
– Chakravarthy, Ghosh
- 1996
|
|
11
|
Modular learning in neural networks
– Ballard
- 1987
|
|
11
|
Hierarchical, unsupervised learning with growing via phase transitions
– Miller, Rose
- 1996
|
|
10
|
Predictive Modular Neural Networks: Applications to Time Series
– Petridis, Kehagias
- 1998
|
|
9
|
M.: A bayesian approach to model selection in hierarchical mixtures-of-experts architectures. Neural Networks 10
– Jacobs, Peng, et al.
- 1997
|
|
3
|
Combining estimates in regression and classi
– LeBlanc, Tibshirani
- 1993
|
|
1
|
A decomposition principle for complexity reduction of arti neural networks, " Neural Networks 9(6
– Zong-ben, Chung-ping
- 1996
|
|
1
|
Combining classi using correspondence analysis
– Merz
- 1998
|
|
1
|
Local regression models," in Statistical Models
– Cleveland, Grosse, et al.
- 1991
|
|
1
|
Local learning in local model networks," in Multiple Model Approaches to Modelling and Control
– Murray-Smith, Johansen
|
