analysis and self-organizing hebbian network
Non-Linear Statistical Analysis and Self-Organizing Hebbian Networks
Neurons learning under an unsupervised Hebbian learning rule can perform a nonlinear generalization of principal component analysis. This relationship between nonlinear PCA and nonlinear neurons is reviewed. The stable fixed points of the neuron learning dynamics correspond to the maxima of the statist,ic optimized under non(cid:173) linear PCA. However, in order to predict. This is shown for a simple model. Methods of statistical mechanics can be used to find the optima of the objective function of non-linear PCA.
Non-Linear Statistical Analysis and Self-Organizing Hebbian Networks
Shapiro, Jonathan L., Prügel-Bennett, Adam
Linear neurons learning under an unsupervised Hebbian rule can learn to perform a linear statistical analysis ofthe input data. This was first shown by Oja (1982), who proposed a learning rule which finds the first principal component of the variance matrix of the input data. Based on this model, Oja (1989), Sanger (1989), and many others have devised numerous neural networks which find many components of this matrix. These networks perform principal component analysis (PCA), a well-known method of statistical analysis.
Non-Linear Statistical Analysis and Self-Organizing Hebbian Networks
Shapiro, Jonathan L., Prügel-Bennett, Adam
Linear neurons learning under an unsupervised Hebbian rule can learn to perform a linear statistical analysis ofthe input data. This was first shown by Oja (1982), who proposed a learning rule which finds the first principal component of the variance matrix of the input data. Based on this model, Oja (1989), Sanger (1989), and many others have devised numerous neural networks which find many components of this matrix. These networks perform principal component analysis (PCA), a well-known method of statistical analysis.
Non-Linear Statistical Analysis and Self-Organizing Hebbian Networks
Shapiro, Jonathan L., Prügel-Bennett, Adam
Linear neurons learning under an unsupervised Hebbian rule can learn to perform a linear statistical analysis ofthe input data. This was first shown by Oja (1982), who proposed a learning rule which finds the first principal component of the variance matrix of the input data. Based on this model, Oja (1989), Sanger (1989), and many others have devised numerous neural networks which find many components of this matrix. These networks perform principal component analysis (PCA), a well-known method of statistical analysis.