AND感知器的权重和偏见是什么?

时间:2018-12-17 19:57:21

标签: python pandas neural-network

我正在实施AND Perceptron,在确定权重和组合的偏向以使其与AND Truth表匹配时遇到困难。

这是我编写的代码:

import pandas as pd

# Set weight1, weight2, and bias
weight1 = 2.0
weight2 = -1.0
bias = -1.0

# Inputs and outputs
test_inputs = [(0, 0), (0, 1), (1, 0), (1, 1)]
correct_outputs = [False, False, False, True]
outputs = []

# Generate and check output
for test_input, correct_output in zip(test_inputs, correct_outputs):
    linear_combination = weight1 * test_input[0] + weight2 * test_input[1] + bias
    output = int(linear_combination >= 0)
    is_correct_string = 'Yes' if output == correct_output else 'No'
    outputs.append([test_input[0], test_input[1], linear_combination, output, is_correct_string])

# Print output
num_wrong = len([output[4] for output in outputs if output[4] == 'No'])
output_frame = pd.DataFrame(outputs, columns=['Input 1', '  Input 2', '  Linear Combination', '  Activation Output', '  Is Correct'])
if not num_wrong:
    print('Nice!  You got it all correct.\n')
else:
    print('You got {} wrong.  Keep trying!\n'.format(num_wrong))
print(output_frame.to_string(index=False))

我必须根据上述值确定权重1,权重2和偏差。当10作为输入时,我得到了一个错误的输出。

感谢您的帮助。

3 个答案:

答案 0 :(得分:5)

  • 等式是对称的:两个输入在功能上是等效的。
  • 以权重作为变量,您在三个(现在两个)变量中有四个(现在三个)不等式。您在哪里无法解决该系统?

系统:

w = weight (same for both inputs)
b = bias

0*w + 0*w + b <= 0
1*w + 0*w + b <= 0
1*w + 1*w + b >  0

这给你留下了

w + b <= 0
2*w + b > 0

您应该能够从那里描述可能的解决方案。

答案 1 :(得分:1)

尝试使用relu激活功能,看看能否解决您的问题

projects.deployments.update

1、1和-1.5应该起作用。

答案 2 :(得分:1)

和感知器:

weight1 = 1.0
weight2 = 1.0
bias = -2.0

或感知器:

weight1 = 1.0
weight2 = 1.0
bias = -1

没有感知器:

weight1 = 1.0
weight2 = -2.0
bias = 0

该偏差可作为调整线性方程的截距。