Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

33

CIS
2005
Springer

favoriteEmaildiscussreport

87views Applied Computing» more CIS 2005»

Training Multi-layer Perceptrons Using MiniMin Approach

14 years 4 months ago

Training Multi-layer Perceptrons Using MiniMin Approach

Download ttic.uchicago.edu

Abstract. Multi-layer perceptrons (MLPs) have been widely used in classification and regression task. How to improve the training speed of MLPs has been an interesting field of research. Instead of the classical method, we try to train MLPs by a MiniMin model which can ensure that the weights of the last layer are optimal at each step. Significant improvement on training speed has been made using our method for several big benchmark data sets.

Liefeng Bo, Ling Wang, Licheng Jiao

Real-time Traffic

CIS 2005 | Multi-Layer Perceptrons | Regression Task | Training Speed |

claim paper

Related Content

» Minimizing Output Error in MultiLayer Perceptrons

» SelfOrganizing MultiLayer Perceptron

» MULP A MultiLayer Perceptron Application to LongTerm OutofSample Time Series Prediction

» Multistyle MLP features for BN transcription

» Forecasting the MagnetoEncephaloGram MEG of Epileptic Patients Using Genetically Optimized...

» Learning weighted similarity measurements for unconstrained face recognition

» Automatic early stopping using cross validation quantifying the criteria

» An Efficient Search Strategy for Feature Selection Using ChowLiu Trees

» Comparison of MLP and GMM Classifiers for Face Verification on XM2VTS

Post Info
More Details (n/a)

Added	26 Jun 2010
Updated	26 Jun 2010
Type	Conference
Year	2005
Where	CIS
Authors	Liefeng Bo, Ling Wang, Licheng Jiao

Comments (0)