| Summary: | Rangkaian neural berdasarkan konsep Perseptron dan Fungsi Asas Jejarian (RBF) sering
digunakan sebagai penge1as corak pintar. Namun, rangkaian neural berasaskan konsep
Perseptron mempunyai kelemahan seperti kadar penumpuan yang perlahan, proses
pencarian pemberat optimum rangkaian yang sering terperangkap di dalam minima
setempat dan sensitif kepada nilai p_embolehubah awalan. Manakala, rangkaian neural
berasaskan konsep RBF berhadapan dengan tiga masalah tipikal seperti fenomena pus at
mati, kehadiran pusat bertindih dan pusat yang terperangkap di dalam minima setempat.
Maka, penyelidikan ini mencadangkan satu seni bina rangkaian. neural baru yang
dinamakan Perseptron Berbilang Lapisan Hibrid Berkelompok atau Clustered-HMLP.
Seni bina rangkaian Clustered-HMLP adalah berasaskan seni bina rangkaian Perseptron
Berbilang Lapisan Hibrid yang diubahsuai melalui penambahan satu lapisan tambahan
yang dinamakan lapisan pusat.
Perseptron based and Radial Basis Function (RBF) neural networks are commonly used
for pattern classification. However, their performances are limited to several weaknesses.
For the Perseptron based neural networks, their training procedures are often trapped at a
local optimum with slow convergence rate and sensitive to initial parameter values.
Whereas, three typical problems for the RBF network are dead centers, centers
redundancy and trapped centers in local minima. Thus, this study introduces a new neural
network architecture called Clustered Hybrid Multilayered Perceptron or ClusteredHMLP.
In this work, the Hybrid Multilayered Perceptron network architecture has been
modified by introducing an additional layer called cluster layer to form the proposed
neural network. The cluster layer concept is adopted from the RBF network architecture.
|
|---|