MACHINE LEARNING QUESTION
A Latin square over the set L{1,2,3} is a 3×3 array such thateach row and column contains exactly one element from L. Train anartificial neural network (with only one hidden layer containingtwo units) which decides whether a given array is a Latin square ornot.
Notes:
1) Use excel to initialize the weights (in a normaldistribution) or just assign random initial values.
2) Use the sigmoid function for all activation units.
3) Use cross-entropy as discussed in class.
4) There should be at least couple of steps in gradient-descentand your solution should have the (initial and updated) weightsafter every step.
Training-data:
1 2 3
2 3 1
OR
PayPal Gateway not configured
OR
PayPal Gateway not configured