Design a model that will decide how to make change for 2298
Solution
learningRate: this is the mastering price used at some point of schooling. The replace of the parameters will be parameters = parameters - learningRate * parameters_gradient. Default fee is 0.01.
learningRateDecay: The studying rate decay. If non-zero, the studying fee (be aware: the sector learningRate will now not exchange price) can be computed after every generation (bypass over the dataset) with: current_learning_rate =learningRate / (1 + iteration * learningRateDecay)
maxIteration: The most range of iteration (passes over the dataset). Default is 25.
shuffleIndices: Boolean which says if the examples could be randomly sampled or no longer. Default is genuine. If fake, the examples can be taken inside the order of the dataset.
hookExample: a probable hook feature to be able to be referred to as (if non-nil) at some point of training after every example forwarded and backwarded thru the network. The function takes (self, instance) as parameters. Default is nil.
hookIteration: a possible hook feature in order to be referred to as (if non-nil) during education after a complete bypass over the dataset. The feature takes (self, new release, currentError) as parameters. Default is nil
