您需要对一组可学习的权重应用 softmax,以确保它们的总和为 1。
我们在自定义层中初始化我们的可学习权重。该层接收我们的 MLP 的输出,并按照我们的逻辑 W1 * Out_MLP1 + W2 * Out_MLP2 + W3 * Out_MLP3 组合它们。输出将是一个形状为 (10,) 的张量。
class W_ADD(Layer):
def __init__(self, n_output):
super(W_ADD, self).__init__()
self.W = tf.Variable(initial_value=tf.random.uniform(shape=[1,1,n_output], minval=0, maxval=1),
trainable=True) # (1,1,n_inputs)
def call(self, inputs):
# inputs is a list of tensor of shape [(n_batch, n_feat), ..., (n_batch, n_feat)]
# expand last dim of each input passed [(n_batch, n_feat, 1), ..., (n_batch, n_feat, 1)]
inputs = [tf.expand_dims(i, -1) for i in inputs]
inputs = Concatenate(axis=-1)(inputs) # (n_batch, n_feat, n_inputs)
weights = tf.nn.softmax(self.W, axis=-1) # (1,1,n_inputs)
# weights sum up to one on last dim
return tf.reduce_sum(weights*inputs, axis=-1) # (n_batch, n_feat)
在这个虚拟示例中,我创建了一个具有 3 个并行 MLP 的网络
inp1 = Input((100))
inp2 = Input((100))
inp3 = Input((100))
x1 = Dense(32, activation='relu')(inp1)
x2 = Dense(32, activation='relu')(inp2)
x3 = Dense(32, activation='relu')(inp3)
x1 = Dense(10, activation='linear')(x1)
x2 = Dense(10, activation='linear')(x2)
x3 = Dense(10, activation='linear')(x3)
mlp_outputs = [x1,x2,x3]
out = W_ADD(n_output=len(mlp_outputs))(mlp_outputs)
m = Model([inp1,inp2,inp3], out)
m.compile('adam','mse')
X1 = np.random.uniform(0,1, (1000,100))
X2 = np.random.uniform(0,1, (1000,100))
X3 = np.random.uniform(0,1, (1000,100))
y = np.random.uniform(0,1, (1000,10))
m.fit([X1,X2,X3], y, epochs=10)
如您所见,这在 N 个并行层的情况下很容易推广