From 5f8d2fae092cc986fd7be775a5ea549ef64a3cd9 Mon Sep 17 00:00:00 2001 From: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com> Date: Wed, 12 Oct 2022 16:46:34 -0400 Subject: [PATCH] Changes learning rate description (#1546) * Fixes learning rate and momentum definitions Signed-off-by: Fanit Kolchina * Update algorithms.md * Makes epsilon, beta1, beta2 and decayRate definitions uniform Signed-off-by: Fanit Kolchina * Changes learning rate description Signed-off-by: Fanit Kolchina Signed-off-by: Fanit Kolchina --- _ml-commons-plugin/algorithms.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/_ml-commons-plugin/algorithms.md b/_ml-commons-plugin/algorithms.md index 685b779e..c0a6ca35 100644 --- a/_ml-commons-plugin/algorithms.md +++ b/_ml-commons-plugin/algorithms.md @@ -65,7 +65,7 @@ Linear regression maps the linear relationship between inputs and outputs. In ML Parameter | Type | Description | Default Value :--- |:--- | :--- | :--- -learningRate | Double | The gradient descent step size at each iteration when moving toward a minimum of a loss function or optimal value. | 0.01 +learningRate | Double | The initial step size used in an iterative optimization algorithm. | 0.01 momentumFactor | Double | The extra weight factors that accelerate the rate at which the weight is adjusted. This helps move the minimization routine out of local minima. | 0 epsilon | Double | The value for stabilizing gradient inversion. | 1.00E-06 beta1 | Double | The exponential decay rates for the moment estimates. | 0.9 @@ -413,7 +413,7 @@ A classification algorithm, logistic regression models the probability of a disc | Parameter | Type | Description | Default Value | |---|---|---|---| -| learningRate | Double | The gradient descent step size at each iteration when moving toward a minimum of a loss function or optimal value | 1 | +| learningRate | Double | The initial step size used in an iterative optimization algorithm. | 1 | | momentumFactor | Double | The extra weight factors that accelerate the rate at which the weight is adjusted. This helps move the minimization routine out of local minima. | 0 | | epsilon | Double | The value for stabilizing gradient inversion. | 0.1 | | beta1 | Double | The exponential decay rates for the moment estimates. | 0.9 |