LearningRate.md (921B)
1 # Learning Rate 2 3 ML L2 4 5 **Definition:** The learning rate is a constant used to narrow in upon some value based on it's distance from an expected value. The further away from the value, the larger the change for a parameter(s) will be. 6 7 See [GradientDescentCode](GradientDescentCode.md) and [[GradientDescent.md]] for an example of when a learning rate would be used and an implementation of it. 8 9 Additionally, learning rate in a higher level sense, with regard to online learning, is how quickly a model will adapt to new data. 10 11 These constants that affect learning rate are called "hyperparameters" which are defined as constants prior to model training that are not built into the model. 12 13 Another term is also the learning schedule. This is the rate at which the learning rate changes. In the case of [GradientDescent](GradientDescent.md) this would be the amount it decreases over time as you narrow in on an optima.