úÎ(š&     Safe¶ !"#None.  Hard sigmoid Prepend a row of onesaddBiases $ (2><3) [20..26](3><3) [ 1.0, 1.0, 1.0 , 20.0, 21.0, 22.0 , 23.0, 24.0, 25.0 ]<Random matrix with elements in the range of [minVal; maxVal]Random sparse matrixQNB: at the moment, the matrix is stored in memory as an ordinary (dense) matrix. Vertical scaling, width, offsetNumber of rows and columnsMinimal and maximal values   None$ÿ $NTC network structure%Trainable part of NTCCustomizable NTC parameters-Modify data before masking (e.g. compression)Input weights (mask) range;Modify data before training or prediction (e.g. add biases)&Reservoir abstraction.WReservoir (a recurrent neural network) is an essential component in the NTC framework.ÒIn this project, we exploit an established analogy between spatially extended and delay systems ^1-3. That makes possible to employ DDEs as a reservoir substrate. The choice of substrate does not affect the & definition below.ÿõ^1 Arecchi, F. T., et al. Two-Dimensional Representation of a Delayed Dynamical System.  Physical Review A, vol. 45, no. 7, Jan. 1992, doi:10.1103/physreva.45.r4225. ^2 Appeltant, L., et al. Information Processing Using a Single Dynamical Node as Complex System.  Nature Communications, vol. 2, 2011, p. 468., doi:10.1038/ncomms1476. ^3 Virtual Chimera States for Delayed-Feedback Systems - Laurent Larger, Bogdan Penkovsky, Yuri Maistrenko. Physical Review Letters - 08 / 2013 Creates an untrained NTC networkDefault NTC parameters'5Substrate-specific low-level reservoir implementation(4Nonlinear transformation performed by an NTC network/NTC training: learn the readout weights offline¡Run prediction using a "clean" (uninitialized) reservoir and then forget the reservoir's state. This can be used for both forecasting and classification tasks.4Input dimension, network nodes, and output dimension( NTC networkInput informationDiscard the first N points6Input matrix of features rows and observations columns-Desired output matrix of observations columnsTrained networkWashout (forget) pointsAInput matrix where measurements are columns and features are rows'Either error string or predicted output  $)*+%,&-./       !"#$%&'()*+,(-./*01!rc-0.1.0.1-AbYOHvz9qG774qbCoJhb63RC.NTC RC.HelpersPaths_rc dde-0.0.0-883TGFnKkKo41RVbeG4OwdNumeric.DDE.Model_filt_rho_fnl_gamma_betaRC MackeyGlassPar_theta_tauBandpassFilteringhsigmoid addBiases randMatrix randSparserandList NTCParameters _preprocess_inputWeightsRange_inputWeightsGenerator _postprocess_reservoirModelnewpar0learnpredictversion getBinDir getLibDir getDynLibDir getDataDir getLibexecDir getSysconfDirgetDataFileNameNTC_outputWeights Reservoir genReservoir forwardPass _inputWeights _reservoir_par _transform