A Constructive Algorithm for Training Cooperative Neural Network Ensembles  

Oleh:

Islam, Md. M. ; Yao, Xin ; Murase, K.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 14 no. 4 (Jul. 2003), page 820-834.
Topik: cooperatives; constructive algorithm; training cooperative; neural network; ensembles

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.8 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Presents a constructive algorithm for training cooperative neural - network ensembles (CNNE s). CNNE combines ensemble architecture design with cooperative training for individual neural networks (NN s) in ensembles. Unlike most previous studies on training ensembles, CNNE puts emphasis on both accuracy and diversity among individual NN s in an ensemble. In order to maintain accuracy among individual NN s, the number of hidden nodes in individual NN s are also determined by a constructive approach. Incremental training based on negative correlation is used in CNNE to train individual NN s for different numbers of training epochs. The use of negative correlation learning and different training epochs for training individual CNNE s emphasis on diversity among individual NN s in an ensemble. CNNE has been tested extensively on a number of benchmark problems in machine learning and neural networks, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, soybean, and Mackey - Glass time series prediction problems. The experimental results show that CNNE can produce NN ensembles with good generalization ability.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali