@ Sebastian Raschka

thanks for your analyzing ,

here is another question, when I use neural network lib routine, can I save the trained network for use at the next time?

Just like the following:

Foo1.py

…

Clf.fit(x,y)

Result_network = clf.save()

…

Foo2.py

…

Clf = Load(result_network)

Res = Clf.predict(newsample)

…

So I needn’t fit the train-set everytime

发件人: scikit-learn [mailto:scikit-learn-bounces+linjia=ruijie.com.cn@python.org] 代表 Sebastian Raschka
发送时间: 2016年11月24日 3:06
收件人: Scikit-learn user and developer mailing list
主题: Re: [scikit-learn] question about using sklearn.neural_network.MLPClassifier？

If you keep everything at their default values, it seems to work -

```py
from sklearn.neural_network import MLPClassifier
X = [[0, 0], [0, 1], [1, 0], [1, 1]]
y = [0, 1, 1, 0]
clf = MLPClassifier(max_iter=1000)
clf.fit(X, y)  
res = clf.predict([[0, 0], [0, 1], [1, 0], [1, 1]])
print(res)
```

The default is set 100 units in the hidden layer, but theoretically, it should work with 2 hidden logistic units (I think that’s the typical textbook/class example). I think what happens is that it gets stuck in local minima depending on the random weight initialization. E.g., the following works just fine:

from sklearn.neural_network import MLPClassifier
X = [[0, 0], [0, 1], [1, 0], [1, 1]]
y = [0, 1, 1, 0]
clf = MLPClassifier(solver='lbfgs', 
                    activation='logistic', 
                    alpha=0.0, 
                    hidden_layer_sizes=(2,),
                    learning_rate_init=0.1,
                    max_iter=1000,
                    random_state=20)
clf.fit(X, y)  
res = clf.predict([[0, 0], [0, 1], [1, 0], [1, 1]])
print(res)

print(clf.loss_)

but changing the random seed to 1 leads to:

[0 1 1 1]

0.34660921283

For comparison, I used a more vanilla MLP (1 hidden layer with 2 units and logistic activation as well; https://github.com/rasbt/python-machine-learning-book/blob/master/code/ch12/ch12.ipynb), essentially resulting in the same problem:

On Nov 23, 2016, at 6:26 AM, linjia@ruijie.com.cn wrote:

Yes，you are right @ Raghav R V, thx!

However, i found the key param is ‘hidden_layer_sizes=[2]’,  I wonder if I misunderstand the meaning of parameter of hidden_layer_sizes?

Is  it related to the topic : http://stackoverflow.com/questions/36819287/mlp-classifier-of-scikit-neuralnetwork-not-working-for-xor


发件人: scikit-learn [mailto:scikit-learn-bounces+linjia=ruijie.com.cn@python.org] 代表 Raghav R V
发送时间: 2016年11月23日 19:04
收件人: Scikit-learn user and developer mailing list
主题: Re: [scikit-learn] question about using sklearn.neural_network.MLPClassifier？

Hi,

If you keep everything at their default values, it seems to work -

```py
from sklearn.neural_network import MLPClassifier
X = [[0, 0], [0, 1], [1, 0], [1, 1]]
y = [0, 1, 1, 0]
clf = MLPClassifier(max_iter=1000)
clf.fit(X, y)  
res = clf.predict([[0, 0], [0, 1], [1, 0], [1, 1]])
print(res)
```

On Wed, Nov 23, 2016 at 10:27 AM, <linjia@ruijie.com.cn> wrote:
Hi everyone

      I try to use sklearn.neural_network.MLPClassifier to test the XOR operation, but I found the result is not satisfied. The following is code, can you tell me if I use the lib incorrectly?

from sklearn.neural_network import MLPClassifier
X = [[0, 0], [0, 1], [1, 0], [1, 1]]
y = [0, 1, 1, 0]
clf = MLPClassifier(solver='adam', activation='logistic', alpha=1e-3, hidden_layer_sizes=(2,), max_iter=1000)
clf.fit(X, y)  
res = clf.predict([[0, 0], [0, 1], [1, 0], [1, 1]])
print(res)


#result is [0 0 0 0], score is 0.5

_______________________________________________
scikit-learn mailing list
scikit-learn@python.org
https://mail.python.org/mailman/listinfo/scikit-learn




-- 
Raghav RV
https://github.com/raghavrv

_______________________________________________
scikit-learn mailing list
scikit-learn@python.org
https://mail.python.org/mailman/listinfo/scikit-learn