In R or python ,you must implement four local random search algorithms. They are:

1. randomized hill climbing

2. simulated annealing

3. a genetic algorithm

4. MIMIC

You will then use the first three algorithms to find good weights for a neural network. In particular, you will use them instead of backprop for the neural network you used in assignment #1 on at least one of the problems you created for assignment #1. Notice that weights in a neural network are continuous and real-valued instead of discrete so you might want to think a little bit about what it means to apply these sorts of algorithms in such a domain.