User:Jeblad/neuralnet notes


 * The huge mismatch between the size (dimensions) of the matrices, that is the order of the computations for each layer, and the rank (independent columns) of the matrices, that is the complexity of the ideal solution
 * Convolutional neural network
 * Expectation–maximization algorithm
 * Scale-invariant feature transform


 * Nomenclature
 * GT, graph transformer/Graph rewriting
 * GTN, graph transformer network
 * HMM, hidden Markov model
 * HOS, heuristic oversegmentation
 * K-NN, K-nearest neighbor
 * NN, neural network
 * OCR, optical character recognition
 * PCA, principal component analysis
 * RBF, radial basis function
 * RS-SVM, reduced-set support vector method/reduced-set support vector machine
 * SDNN, space displacement neural network
 * SVM, support vector method/support vector machine
 * TDNN, time delay neural network
 * V-SVM, virtual support vector method/virtual support vector machine
 * ResNets, Residual neural networks (Residual network is about flow graphs)