From d5a6c81dc55057ba437efe417992c0521e87c754 Mon Sep 17 00:00:00 2001 From: wangmeng28 Date: Mon, 20 Nov 2017 11:48:52 +0800 Subject: [PATCH] Update docs for factorization machine layer --- paddle/gserver/layers/FactorizationMachineLayer.h | 5 ++--- python/paddle/trainer_config_helpers/layers.py | 5 ++--- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/paddle/gserver/layers/FactorizationMachineLayer.h b/paddle/gserver/layers/FactorizationMachineLayer.h index 85ac175657c..3bc36daaab3 100644 --- a/paddle/gserver/layers/FactorizationMachineLayer.h +++ b/paddle/gserver/layers/FactorizationMachineLayer.h @@ -36,8 +36,7 @@ namespace paddle { * * The detailed calculation for forward and backward can be found at this paper: * - * Rendle, Steffen. Factorization machines. IEEE 10th International - * Conference on Data Mining (ICDM). IEEE, 2010. + * Factorization machines. * * The config file api is factorization_machine. */ @@ -59,7 +58,7 @@ private: // The result of input matrix * latent vector matrix that will be used in // both forward and backward step MatrixPtr inputMulFactor_; - // Temporary calculation result store + // Store temporary calculation result MatrixPtr tmpOut_; MatrixPtr tmpSum_; // Negative identity matrix diff --git a/python/paddle/trainer_config_helpers/layers.py b/python/paddle/trainer_config_helpers/layers.py index cc1bf923dd0..37214a53d36 100644 --- a/python/paddle/trainer_config_helpers/layers.py +++ b/python/paddle/trainer_config_helpers/layers.py @@ -3876,7 +3876,7 @@ def recurrent_layer(input, :type input: LayerOutput :param act: Activation type. TanhActivation is the default activation. :type act: BaseActivation - :param bias_attr: The parameter attribute for bias. If this parameter is set to + :param bias_attr: The parameter attribute for bias. If this parameter is set to False or an object whose type is not ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. @@ -7307,8 +7307,7 @@ def factorization_machine(input, each latent vector is k. For details of Factorization Machine, please refer to the paper: - Rendle, Steffen. Factorization machines. IEEE 10th International - Conference on Data Mining (ICDM). IEEE, 2010. + Factorization machines. .. code-block:: python factor_machine = factorization_machine(input=input_layer, factor_size=10) -- GitLab