apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-14 14:32:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

mappings, including tests

Browse source
This commit is contained in:
James Hensman 2015-03-26 11:27:20 +00:00
parent cf0e29b207
commit 624117eaac
6 changed files with 141 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

33
GPy/mappings/mlp.py
View file

@ -11,32 +11,45 @@ class MLP(Mapping):
"""
def __init__(self, input_dim=1, output_dim=1, hidden_dim=3, name='mlpmap'):
super(MLP).__init__(self, input_dim=input_dim, output_dim=output_dim, name=name)
super(MLP, self).__init__(input_dim=input_dim, output_dim=output_dim, name=name)
self.hidden_dim = hidden_dim
self.W1 = Param('W1', np.random.randn(self.input_dim, self.hidden_dim))
self.b1 = Param('b1', np.random.randn(self.hidden_dim))
self.W2 = Param('W2', np.random.randn(self.hidden_dim, self.output_dim))
self.b2 = Param('b2', np.random.randn(self.output_dim))
self.link_parameters(self.W1, self.b1, self.W2, self.b2)
def f(self, X):
N, D = X.shape
activations = np.tanh(np.dot(X,self.W1) + self.b1)
self.out = np.dot(self.activations,self.W2) + self.b2
return self.output_fn(self.out)
layer1 = np.dot(X, self.W1) + self.b1
activations = np.tanh(layer1)
return np.dot(activations, self.W2) + self.b2
def update_gradients(self, dL_dF, X):
activations = np.tanh(np.dot(X,self.W1) + self.b1)
layer1 = np.dot(X,self.W1) + self.b1
activations = np.tanh(layer1)
#Evaluate second-layer gradients.
self.W2.gradient = np.dot(activations.T, dL_dF)
self.b2.gradient = np.sum(dL_dF, 0)
# Backpropagation to hidden layer.
delta_hid = np.dot(dL_dF, self.W2.T) * (1.0 - activations**2)
dL_dact = np.dot(dL_dF, self.W2.T)
dL_dlayer1 = dL_dact / np.square(np.cosh(layer1))
# Finally, evaluate the first-layer gradients.
self.W1.gradients = np.dot(X.T,delta_hid)
self.b1.gradients = np.sum(delta_hid, 0)
self.W1.gradient = np.dot(X.T,dL_dlayer1)
self.b1.gradient = np.sum(dL_dlayer1, 0)
def gradients_X(self, dL_dF, X):
layer1 = np.dot(X,self.W1) + self.b1
activations = np.tanh(layer1)
# Backpropagation to hidden layer.
dL_dact = np.dot(dL_dF, self.W2.T)
dL_dlayer1 = dL_dact / np.square(np.cosh(layer1))
return np.dot(dL_dlayer1, self.W1.T)