Class RNN

constructor

• new RNN(
      method?: "rnn" | "lstm" | "gru",
      window?: number,
      unit?: number,
      out_size?: number,
      optimizer?: string,
  ): RNN

  Parameters

  • Optionalmethod: "rnn" | "lstm" | "gru"

    Method name

  • Optionalwindow: number

    Window size

  • Optionalunit: number

    Size of recurrent unit

  • Optionalout_size: number

    Output size

  • Optionaloptimizer: string

    Optimizer of the network

  Returns RNN

_epoch

_layers

_method

_model

_window

epoch

• get epoch(): number

  Epoch

  Returns number

method

• get method(): "rnn" | "lstm" | "gru"

  Method

  Returns "rnn" | "lstm" | "gru"

fit

• fit(
      train_x: number[][],
      train_y: number[][],
      iteration: number,
      rate: number,
      batch: number,
  ): number

  Fit model.

  Parameters

  • train_x: number[][]

    Training data

  • train_y: number[][]

    Target values

  • iteration: number

    Iteration count

  • rate: number

    Learning rate

  • batch: number

    Batch size

  Returns number

  Loss value

predict

• predict(data: number[][], k: number): number[][]

  Returns predicted future values.

  Parameters

  • data: number[][]

    Sample data

  • k: number

    Prediction count

  Returns number[][]

  Predicted values