Multilayer Perceptron Networks
Abstract
The paper focuses on the various neural network techniques consisting of Multilayer perceptron (MLP) neural community. The diverse components of the neural networks techniques are noted inside the paper at the side of the advantages and some of the drawbacks. Neural networks are taken the different strategies to the trouble fixing than that of the conventional computer systems. The neural network fashions are trained with measured values of the sphere power at the arbitrary factors of the network. Additionally the paper researched some essential issues regarding with the functionality of the multilayer perceptron’s with one or hidden layer. This result may be very useful inside the analyzing pattern of diverse varieties of popularity and database retrieval. The neural networks are also beneficial inside the photo processing for image recognition.
Full Text:
PDFReferences
S. and Kiebel J. 2012. Recognizing Recurrent Neural Networks (rRNN): Bayesian Inference for Recurrent Neural Networks. arXiv: 1201, 4339v1.
Calcagno G. and StaianoAntonino. 2010. A Multilayer Neural Network-based approach for the identification of responsiveness to interferon therapy in multiple sclerosis patients. Information Sciences. Vol. 180, Issue 21, 41534163.
Hill T, O’Connor M, Remus W. Neural Networks Models for Time Series Forecasts, Management Sciences, doi: 10.1287/mnsc.42.7.1082 1996; 42:1082-1092.
Hann TH, Steurer E. Much ado about nothing? Exchange rate forecasting: Neural networks vs. linear models using monthly and weekly data. Neurocomputing 1996; 10:323339.
K. Fukushima. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, 36(4):193–202, 1980.
V. Jain and E. Learned-Miller. Fddb: A benchmark for face detection in unconstrained settings. Technical Report UM-CS-2010-009, University of Massachusetts, Amherst, 2010.
Refbacks
- There are currently no refbacks.