Firm B has the faster learning rate.
Why is learning rate important?
In general, a high learning rate makes a model learn faster at the expense of a less than optimal final set of weights. A smaller learning rate allows the model to learn a more optimal or overall optimal set of weights, but can take a significant amount of time to train.
What is a good learning rate?
The range of values to consider for the learning rate is less than 1.0 and greater than 10^-6. The traditional default value for the learning rate is 0.1 or 0.01, which is a good starting point for your problem.
What happens if the learning rate is too high?
If the learning rate is set too low, the network weights are updated very little, and training progresses very slowly. However, setting the learning rate too high can lead to unwanted and erratic behavior of the loss function.
Learn more about learning rate here:- https://brainly.com/question/28026849
#SPJ4
