Network complexity and learning efficiency of constructive learning algorithms

Fang, Wai-Chi; Lacher, R. C.

doi:10.1109/icnn.1994.374191

Cited by 13 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The constructive feedforward neural network considered in this paper may yield improved approximation and representation capabilities as compared to fixed structure feedforward neural networks. Other architectures have also been developed in the literature, such as the stack learning algorithm [9] and adding-and-deleting algorithm [22]. The stack learning algorithm begins with a minimal structure consisting of input and output units only, similar to the initial network in cascade correlation algorithm.…”

Section: B Limitations Of the Current Constructive Feedforward Neuramentioning

confidence: 99%

Facial Expression Recognition Using Constructive Feedforward Neural Networks

Khorasani

2004

IEEE Trans. Syst., Man, Cybern. B

202

View full text Add to dashboard Cite

A new technique for facial expression recognition is proposed, which uses the two-dimensional (2-D) discrete cosine transform (DCT) over the entire face image as a feature detector and a constructive one-hidden-layer feedforward neural network as a facial expression classifier. An input-side pruning technique, proposed previously by the authors, is also incorporated into the constructive learning process to reduce the network size without sacrificing the performance of the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having five facial expression images (neutral, smile, anger, sadness, and surprise). Images of 40 men are used for network training, and the remaining images of 20 men are used for generalization and testing. Confusion matrices calculated in both network training and generalization for four facial expressions (smile, anger, sadness, and surprise) are used to evaluate the performance of the trained network. It is demonstrated that the best recognition rates are 100% and 93.75% (without rejection), for the training and generalizing images, respectively. Furthermore, the input-side weights of the constructed network are reduced by approximately 30% using our pruning method. In comparison with the fixed structure back propagation-based recognition methods in the literature, the proposed technique constructs one-hidden-layer feedforward neural network with fewer number of hidden units and weights, while simultaneously provide improved generalization and recognition performance capabilities.

show abstract

Section: B Limitations Of the Current Constructive Feedforward Neuramentioning

confidence: 99%

Facial Expression Recognition Using Constructive Feedforward Neural Networks

Khorasani

2004

IEEE Trans. Syst., Man, Cybern. B

202

View full text Add to dashboard Cite

show abstract

“…This allows to produce smaller architectures than those required by the solutions presented in [11], [12], [13] with the corresponding improvements in training effectiveness and efficiency.…”

Section: A Sinusoidal Functionmentioning

confidence: 95%

Boosting Learning Machines with Function Compositions to Avoid Local Minima in Regression Problems

Zegers

Correa

2007

2007 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

show abstract

“…The constructive multilayer FNN proposed in this paper provides also a suboptimal solution to Eqs. (1) and (2).…”

Section: Neural Networkmentioning

confidence: 99%

Strategies for constructive neural networks and its application to regression models

Nong

2012

2012 International Conference on Computer Science and Information Processing (CSIP)

View full text Add to dashboard Cite

Regression problem is an important application area for neural networks (NNs). Among a large number of existing NN architectures, the feedfOIward NN (FNN) paradigm is one of the most widely used structures. Although one-hidden-Iayer feedforward neural networks (OHL-FNNs) have simple structures, they possess interesting representational and learning capabilities. fu this paper, we are interested particularly in incremental constructive training of OHL FNNs. fu the proposed incremental constructive training schemes for an OHL-FNN, input-side training and output-side training may be separated in order to reduce the training time. A new technique is proposed to scale the error signal during the constructive learning process to improve the input-side training efficiency and to obtain better generalization performance. Two pruning methods for removing the input side redundant connections have also been applied. Numerical simulations demonstrate the potential and advantages of the proposed strategies when compared to other existing techniques in the literature.

show abstract

Network complexity and learning efficiency of constructive learning algorithms

Cited by 13 publications

References 5 publications

Facial Expression Recognition Using Constructive Feedforward Neural Networks

Facial Expression Recognition Using Constructive Feedforward Neural Networks

Boosting Learning Machines with Function Compositions to Avoid Local Minima in Regression Problems

Strategies for constructive neural networks and its application to regression models

Contact Info

Product

Resources

About