def build_feedforward_multilayered(input_number = 2, hidden_numbers = [2], output_number = 1, hidden_function = "tanh", output_function = "logsig"):
net = network()
net.num_of_inputs = input_number
inputs = range(input_number)
biasnode = net.bias_node
#Hidden layers
prev_layer = inputs
for hidden_number in hidden_numbers:
current_layer = []
for i in xrange(int(hidden_number)):
hidden = node(hidden_function)
connect_node(hidden, biasnode)
connect_nodes(hidden, prev_layer)
net.hidden_nodes.append(hidden)
current_layer.append(hidden)
prev_layer = current_layer
#Output nodes
for i in xrange(int(output_number)):
output = node(output_function)
connect_node(output, biasnode)
connect_nodes(output, prev_layer)
net.output_nodes.append(output)
return net
def test4NodesTest(self):
net = network()
#input_number = 2 # 2 inputs
#net.num_of_inputs = input_number
#inputs = range(input_number)
biasnode = net.bias_node
inputs = range(2)
my_node = Node("linear")
for in_idx in inputs:
#connect with inputs with weight 1.0
connect_node(my_node, in_idx, 1.0)
out_val = my_node.output([1.0,1.0])
print("Output of node with (1,1) is: {0}".format(out_val))
assert(out_val == 2.0) # Simply the sum of the inputs
#connect to bias
connect_node(my_node, biasnode, 1.0)
out_val = my_node.output([1.0,1.0])
print("Output of node with (1,1) and bias is: {0}".format(out_val))
assert(out_val == 3.0) # Simply the sum of the inputs
