Optimizee for MNIST

The fitness function to optimize is the MNIST performance.

MNISTOptimizee

class l2l.optimizees.mnist.optimizee.MNISTOptimizee(traj, parameters)

Bases: l2l.optimizees.optimizee.Optimizee

Implements a simple function optimizee. Functions are generated using the FunctionGenerator. NOTE: Make sure the optimizee_fitness_weights is set to (-1,) to minimize the value of the function

Parameters:

• traj – The trajectory used to conduct the optimization.
• parameters – Instance of namedtuple() MNISTOptimizeeParameters

create_individual()

Creates a random value of parameter within given bounds

bounding_func(individual)

Bounds the individual within the required bounds via coordinate clipping

simulate(traj)

Returns the value of the function chosen during initialization

Parameters:traj (Trajectory) – Trajectory Returns:a single element tuple containing the value of the chosen function

MNISTOptimizeeParameters

class l2l.optimizees.mnist.optimizee.MNISTOptimizeeParameters(n_hidden, seed, use_small_mnist)

n_hidden

seed

use_small_mnist