def test_or_nn(verbose=0):
x, y = create_or_nn_data()
nn = NeuralNetwork(x, y, 4, 1)
nn.feedforward()
if verbose > 0:
print("OR 1 " + str(nn.loss()))
print("NN output " + str(nn._output))
print(nn.accuracy_precision())
assert nn.loss() < .04
def test_ttt_nn(verbose=0):
x, y = load_tictactoe_csv("tic-tac-toe-1.csv")
nn = NeuralNetwork(x, y, 4, .1)
nn.load_4_layer_ttt_network()
nn.feedforward()
if verbose > 0:
print("NN 1 " + str(nn.loss()))
print("NN output " + str(nn._output))
print(nn.accuracy_precision())
assert nn.loss() < .02
class NeuralNetworkEvaluator(Evaluator):
def __init__(self, weights=None):
self.weights = weights
super().__init__(weights)
self.network = NeuralNetwork(input_shape=(1, 22))
self.genome_len = self.network.num_nodes
if self.weights is not None:
self.network.weights = self.network.weights_to_ndarray(self.weights)
else:
self.weights = self.network.weights_to_list()
self.genome = self.weights
def eval(self, engine):
self.engine = engine
state_eval = 0
if self.engine.game_state is not None:
if self.engine.game_state == 0:
return 0
else:
return 10000 if self.engine.game_state == 1 else -10000
state_eval = self.gene_eval()
return state_eval
def gene_eval(self):
feature_vec = []
for player in [1, 2]:
player_vec = []
if self.engine.game_state is None:
self.player = player
for feature in self.features:
player_vec.append(feature())
feature_vec.extend(player_vec)
return self.network.feedforward(feature_vec)
def run_network(learning_rate, hidden_nodes):
brain = NeuralNetwork(784, hidden_nodes, 10)
brain.set_learning_rate(learning_rate)
counter = 0
for image, label in zip(training_images, training_labels):
counter += 1
print(
f"Backward propogating the {counter} image, which was a {label} with array: {labels_dict[label]}."
)
brain.train(image.ravel(), labels_dict[label])
#if counter > 20_000: break
#print(brain.weights_ho[2:3, 2:4])
correct = 0
for i in range(len(testing_images)):
output = brain.feedforward(testing_images[i].ravel())
output = output.ravel()
#print(testing_images[i].ravel())
print(output)
print(
f"The letter was thought to be {output.argmax()} by the Neural network, but was actually {testing_labels[i]}."
)
if output.argmax() == testing_labels[i]:
correct += 1
print("IT WAS CORRECT!")
print(correct / len(testing_images))
return correct / len(testing_images)
def test(x):
correct_pred = 0
for i in range(x):
brain = NeuralNetwork(2, 4, 1)
for i in range(100000):
j = randint(0, 3)
brain.train(inputs[j], targets[j])
t1 = output(brain.feedforward([0, 0])[0][0])
t2 = output(brain.feedforward([1, 1])[0][0])
t3 = output(brain.feedforward([0, 1])[0][0])
t4 = output(brain.feedforward([1, 0])[0][0])
print(t1, t2, t3, t4)
if targets[0][0] == t1 and targets[1][0] == t2 and targets[2][
0] == t3 and targets[3][0] == t4:
correct_pred += 1
classification_rate = (correct_pred / x) * 100
message = "Classification rate: " + str(classification_rate) + "%"
return message
]
targets = [
[0],
[1],
[1],
[0],
]
for _ in range(10000):
i = randint(0, len(data) - 1)
nn.train(data[i], targets[i], 0.1)
print(nn.feedforward(data[0]).rows)
print(nn.feedforward(data[1]).rows)
print(nn.feedforward(data[2]).rows)
print(nn.feedforward(data[3]).rows)
print("----")
# NOT example
nn = NeuralNetwork([1, 1, 1])
data = [[0], [1]]
targets = [[1], [0]]
for _ in range(0):
i = randint(0, len(data) - 1)
nn.train(data[i], targets[i], 0.1)
return True
if output == [0, 1]:
return False
nn = NeuralNetwork(2, 1, 2)
# start training for AND operation
for i in range(1000):
nn.train([1, 1], [1, 0])
nn.train([1, 0], [0, 1])
nn.train([0, 0], [0, 1])
nn.train([0, 1], [0, 1])
# end training
print('AND OPERATION')
print([1,0], ' => ', pretty_print(nn.feedforward([1,0])))
print([1,1], ' => ', pretty_print(nn.feedforward([1,1])))
print([0,1], ' => ', pretty_print(nn.feedforward([0,1])))
print([0,0], ' => ', pretty_print(nn.feedforward([0,0])))
#start training for XOR operation
nn = NeuralNetwork(2, 2, 1)
training_data = [
{'i': [1, 1], 'o': [0]},
{'i': [1, 0], 'o': [1]},
{'i': [0, 0], 'o': [0]},
{'i': [0, 1], 'o': [1]},
]
for i in range(50000):
data = training_data[random.randint(0, 3)]
