Infinite-dimensional multilayer perceptrons
IEEE TRANSACTIONS ON NEURAL NETWORKS, cilt.7, sa.4, ss.889-896, 1996 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 7 Sayı: 4
- Basım Tarihi: 1996
- Doi Numarası: 10.1109/72.508932
- Dergi Adı: IEEE TRANSACTIONS ON NEURAL NETWORKS
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Computer & Applied Sciences
- Sayfa Sayıları: ss.889-896
- Orta Doğu Teknik Üniversitesi Adresli: Evet
Özet
In this paper a new multilayer perceptron (MLP) structure is introduced to simulate nonlinear transformations on infinite-dimensional function spaces. This extension is achieved by replacing discrete neurons by a continuum of neurons, summations by integrations and weight matrices by kernels of integral transforms, Variational techniques have been employed for the analysis and training of the infinite-dimensional MLP (IDMLP). The training problem of IDMLP is solved by the Lagrange multiplier technique yielding the coupled state and adjoint state integro-difference equations. A steepest descent-like algorithm is used to construct the required kernel and threshold functions. Finally, some results are presented to show the performance of the new IDMLP.