Klasifikasi Pola yang tak Dapat Dipisahkan Secara Linier (Non-Linearly Separable Pattern) Menggunakan Jaringan Syaraf Tiruan Perceptron Multi-Layer  

Oleh:

Y. Sigit Purnomo W.P.

Jenis: Article from Journal - ilmiah nasional
Dalam koleksi: Jurnal Teknologi Industri vol. 5 no. 3 (Jul. 2001), page 177-184.
Topik: Non-Linearly Separable Pattern; Multi Layer Perceptron; Neural Networks; Pattern Classification
Fulltext: Klasifikasi Pola yang Tak Dapat Dipisahkan.pdf (2.5MB)

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: JJ83.3 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Non-linearly separable pattern is pattern that can 't be simply classified by the simple line (linear). This pattern classification can 't be done with the single-layer peceptron neural network, but with the complex neural network that is the multi-layer peceptron (MLP) or backpropagation. The pattern classification for this cause influenced by many factors, such as initial weight matrix and bias, number of neuron, number of maximum epochs and the learning rate for the training process that can be learnt from the plot of total square error.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali