Adam optimizer as described in Adam - A Method for StochasticOptimization.

optimizer_adam(lr = 0.001, beta_1 = 0.9, beta_2 = 0.999, epsilon = NULL, decay = 0, amsgrad = FALSE, clipnorm = NULL, clipvalue = NULL)

lr | float >= 0. Learning rate. |
---|---|

beta_1 | The exponential decay rate for the 1st moment estimates. float, 0 < beta < 1. Generally close to 1. |

beta_2 | The exponential decay rate for the 2nd moment estimates. float, 0 < beta < 1. Generally close to 1. |

epsilon | float >= 0. Fuzz factor. If |

decay | float >= 0. Learning rate decay over each update. |

amsgrad | Whether to apply the AMSGrad variant of this algorithm from the paper "On the Convergence of Adam and Beyond". |

clipnorm | Gradients will be clipped when their L2 norm exceeds this value. |

clipvalue | Gradients will be clipped when their absolute value exceeds this value. |

Default parameters follow those provided in the original paper.

Other optimizers: `optimizer_adadelta`

,
`optimizer_adagrad`

,
`optimizer_adamax`

,
`optimizer_nadam`

,
`optimizer_rmsprop`

,
`optimizer_sgd`