Logo
  • Getting Started
    • Installation guide
    • Mass-spring-damper Estimator
    • Reacher Estimator
    • Applications
    • Tutorials
  • Modely Class
    • Modely
      • Modely.constants
      • Modely.internals
      • Modely.json
      • Modely.neuralized
      • Modely.parameters
      • Modely.resetSeed()
      • Modely.states
      • Modely.traced
      • Modely.trainAndAnalyze()
  • Model Definition
    • Input module
      • Input
        • Input.json_name
        • Input.name
        • Input.dim
        • Input.json
        • Input.clearNames()
        • Input.closedLoop()
        • Input.connect()
        • Input.last()
        • Input.names
        • Input.next()
        • Input.s()
        • Input.sw()
        • Input.tw()
        • Input.z()
    • Parameter module
      • Constant
        • Constant.name
        • Constant.dim
        • Constant.json
      • SampleTime
        • SampleTime.name
        • SampleTime.dim
        • SampleTime.json
      • Parameter
        • Parameter.name
        • Parameter.dim
        • Parameter.json
    • Initializer module
      • init_constant()
      • init_negexp()
      • init_exp()
      • init_lin()
    • Output module
      • Output
        • Output.name
        • Output.json
        • Output.dim
        • Output.clearNames()
        • Output.names
    • Building blocks
      • Activation module
        • Relu
        • ELU
        • Sigmoid
        • Softmax
        • Identity
      • Arithmetic module
        • Add
        • Sub
        • Mul
        • Div
        • Pow
        • Neg
      • FIR module
        • Fir
      • Fuzzify module
        • Fuzzify
      • EquationLearner module
        • EquationLearner
      • Linear module
        • Linear
      • Localmodel module
        • LocalModel
      • Part module
        • Part
        • Select
        • SamplePart
        • SampleSelect
        • TimePart
      • Trigonometric module
        • Sin
        • Cos
        • Tan
        • Tanh
        • Cosh
        • Sech
      • Parametric Function module
        • ParamFun
  • Dataset Creation
    • Data Loader module
      • getSamples()
      • filterData()
      • resamplingData()
      • loadData()
  • Model Composition
    • Stream-level composition
      • Stream
        • Stream.closedLoop()
        • Stream.connect()
        • Stream.delay()
        • Stream.s()
        • Stream.sw()
        • Stream.tw()
        • Stream.z()
    • Model-level composition
      • addModel()
      • removeModel()
      • addConnect()
      • addClosedLoop()
      • removeConnection()
      • neuralizeModel()
    • Composition at Training and Inference Time
  • Training
    • Training module
      • addMinimize()
      • removeMinimize()
      • getTrainingInfo()
      • trainModel()
    • Optimizer module
      • SGD
        • SGD.name
        • SGD.lr
        • SGD.momentum
        • SGD.dampening
        • SGD.weight_decay
        • SGD.nesterov
        • SGD.add_defaults()
        • SGD.set_defaults()
        • SGD.set_params()
        • SGD.set_params_to_train()
        • SGD.unfold()
      • Adam
        • Adam.name
        • Adam.lr
        • Adam.betas
        • Adam.eps
        • Adam.weight_decay
        • Adam.amsgrad
        • Adam.add_defaults()
        • Adam.set_defaults()
        • Adam.set_params()
        • Adam.set_params_to_train()
        • Adam.unfold()
    • Early Stopping module
      • early_stop_patience()
      • select_best_model()
      • mean_stopping()
      • standard_early_stopping()
  • Validation
    • Validation Module
      • analyzeModel()
  • Inference
    • Inference module
      • Composer.__call__()
  • Model Export
    • Export module
      • saveTorchModel()
      • loadTorchModel()
      • saveModel()
      • loadModel()
      • exportPythonModel()
      • importPythonModel()
      • exportONNX()
      • onnxInference()
      • exportReport()
  • Tutorials
    • Load Data
      • Load a dataset using a directory
      • Load a dataset from a custom dictionary
      • Load a dataset from a pandas DataFrame
      • Resampling a pandas DataFrame
      • Get Samples from the Dataset
    • Training
      • Basic Parameters and Usage
      • Recurrent Training
      • Set different weight for the minimization functions
      • Setting the Optimizer
      • Early stopping and Best Model
      • Train and Analyze
    • Inference
      • Simple inference
      • Inference with a sampled data
      • Closed Loop and Connect during Inference
      • Recurrent inference with prediction samples
      • Recurrent inference with number of samples
    • Import/Export Network
      • Save/Load the model definition in a json file
      • Save/Load network parameters in a pickle file
      • Export/Import pytorch model
      • Export the network to an ONNX format
      • ONNX inference
      • Export training and validation report
      • Example - Longitudinal dynamics of a vehicle (Non recurrent version export)
      • Example - Longitudinal dynamics of a vehicle (Recurrent version export)
    • Fir Layer
      • Basic Usage Example
      • Setting a Weight and a Bias Name
      • Passing a Parameter to the Fir Relation
      • Initialize the parameters
      • Adding the Dropout
    • Fuzzify Layer
      • Basic Usage
      • Rectangular function
      • Custom functions
      • Multiple custom functions
      • Repeated custom functions
    • Linear Layer
      • Basic Usage
      • Passing a Parameter
      • Initialization functions
      • Dropout
    • Local Model
      • Basic usage
      • Passing an output function
      • Passing a custom function
      • Custom function with multiple activations
      • Passing indexes
    • Constant and Parameter
      • Basic Usage
      • Using a Parameter inside another block
      • Parametric functions
      • Arithmetic functions with Parameters and Constants
      • SampleTime
      • Initialization functions
    • Parametric Functions
      • Basic usage
      • Parameter dimension
      • Passing custom parameters
      • Parametric function with different parameters
      • Parametric functions with Constants
      • Mapping over a batch
    • Partitioning
      • Part
      • Select
      • Concatenate
      • SamplePart
      • SampleSelect
      • TimeConcatenate
    • State Variables
      • State Definition
      • Closed Loop
      • Connect
      • Connect two models together
      • Recurrent Train
      • Clear State
      • State update at training time
    • Equation Learner Layer
      • Basic Usage
      • Input layer
      • Input layer and output layer
      • Multiple inputs
      • Multi-parameter functions
      • Using custom parametric functions
      • Using parametric functions with parameters
      • Parametric functions and fuzzy layers
      • Cascade Equation Learner Blocks
    • Interpolation Layer
      • Basic Usage
      • Linear Interpolation
  • Overview: module code

All modules for which code is available

  • nnodely.basic.optimizer
  • nnodely.basic.relation
  • nnodely.layers.activation
  • nnodely.layers.arithmetic
  • nnodely.layers.equationlearner
  • nnodely.layers.fir
  • nnodely.layers.fuzzify
  • nnodely.layers.input
  • nnodely.layers.linear
  • nnodely.layers.localmodel
  • nnodely.layers.output
  • nnodely.layers.parameter
  • nnodely.layers.parametricfunction
  • nnodely.layers.part
  • nnodely.layers.trigonometric
  • nnodely.nnodely
  • nnodely.operators.composer
  • nnodely.support.earlystopping
  • nnodely.support.initializer

© Copyright .

Built with Sphinx using a theme provided by Read the Docs.