A multilayer perceptron MLP is given below with initial weig

A multi-layer perceptron (MLP) is given below with initial weights. Please train the MLP by using the following training data set. You need to write down the detailed process how each weight is recalculated for just one iteration (using all training instance once).

Deliverable: clearly show how each weight is recalculated for the first iteration.

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