回答此问题可获得 20 贡献值,回答如果被采纳可获得 50 分。
<p>我知道感知器只能在线性可分离集上正确工作,比如NAND、AND、OR函数的输出。我一直在读<a href="http://en.wikipedia.org/wiki/Perceptron" rel="nofollow">Wikipedia's entry on the perceptron</a>,并开始研究它的代码。在</p>
<p>当它是一个可分离的层时,它不应该是线性的。在</p>
<pre><code>#xor
print ("xor")
t_s = [((1, 1, 1), 0), ((1, 0, 1), 1), ((1, 1, 0), 1), ((1, 1, 1), 0)]
threshold = 0.5
learning_rate = 0.1
w = [0, 0, 0]
def dot_product(values, weights):
return sum(value * weight for value, weight in zip(values, weights))
def train_perceptron(threshold, learning_rate, weights, training_set):
while True:
#print('-' * 60)
error_count = 0
for input_vector, desired_output in training_set:
#print(weights)
result = dot_product(input_vector, weights) > threshold
error = desired_output - result
if error != 0:
error_count += 1
for index, value in enumerate(input_vector):
weights[index] += learning_rate * error * value
if error_count == 0: #iterate till there's no error
break
return training_set
t_s = train_perceptron(threshold, learning_rate, w, t_s)
t_s = [(a[1:], b) for a, b in t_s]
for a, b in t_s:
print "input: " + str(a) + ", output: " + str(b)
</code></pre>
<p><a href="http://ideone.com/kdypyJ" rel="nofollow">The output for this Ideone run is correct for XOR</a>。怎么会?在</p>
^{pr2}$