def __init__(self):
NeuralNetwork.__init__(self, 1, 1)
# Get the layer and modify the values for the layer to suit the AND operation
# The threshold for True or False is 0.5
self.layer = NeuralNetwork.getlayer(self, 0)
self.layer[0] = 5
self.layer[1] = -6
return
def __init__(self):
NeuralNetwork.__init__(self, [2, 2, 1])
layer = []
layer.append(self.getLayer(0))
layer.append(self.getLayer(1))
self.network[0] = torch.from_numpy(
np.array([[20.0, -20.0], [20.0, -20.0], [-10.0, 30.0]]))
self.network[1] = torch.from_numpy(np.array([20.0, 20.0, -30.0]))
def __init__(self, data_set_name, layer_sizes, P2_algorithm_basis=None):
NeuralNetwork.__init__(self, data_set_name, layer_sizes)
self.network_name = 'RBF'
self.logger = Logger('DEMO')
self.P2_algorithm_basis = P2_algorithm_basis
# instance of Project 2 API - a single class for accessing all things needed from P2
self.P2API = P2API(data_set_name, self.P2_algorithm_basis)
# list of tuples for RBF neuron values, each tuple is (beta, mu)
# beta at spot 1 and vector is at spot 0
self.rbf_neurons = []
def __init__(self):
NeuralNetwork.__init__(self, 2, 2, 1)
# Get the layer and modify the values for the layer to suit the AND operation
# The threshold for True or False is 0.5
self.layer = NeuralNetwork.getlayer(self, 0)
self.layer[0, :] = -5
self.layer[1, 0] = 4
self.layer[2, 0] = 4
self.layer[1, 1] = 6
self.layer[2, 1] = 6
self.layer = NeuralNetwork.getlayer(self, 1)
self.layer[0] = -1
self.layer[1] = -2
self.layer[2] = 2.5
return
def __init__(self, data_set_name, layer_sizes):
NeuralNetwork.__init__(self, data_set_name, layer_sizes)
self.logger = Logger('DEMO') # configure class-level log level here
self.network_name = 'MLP'
def __init__(self):
NeuralNetwork.__init__(self, [2, 1])
layer = self.getLayer(0)
self.network[0] = torch.from_numpy(np.array([20.0, 20.0, -10.0]))
def __init__(self):
self.layersizes = (784, 128, 10)
NeuralNetwork.__init__(self, self.layersizes)
