參考：https://docs.pymc.io/getting_started.html

https://twiecki.io/blog/2016/06/01/bayesian-deep-learning/

1、生成非線性可分的二分類數(shù)據(jù)

%matplotlib inline import theano import pymc3 as pm import sklearn import numpy as np import matplotlib.pyplot as plt import seaborn as sns from warnings import filterwarnings filterwarnings('ignore') sns.set_style('white') from sklearn import datasets from sklearn.preprocessing import scale from sklearn.cross_validation import train_test_split from sklearn.datasets import make_moons X, Y = make_moons(noise=0.2, random_state=0, n_samples=1000) X = scale(X) X = X.astype(float) Y = Y.astype(float) X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5) fig, ax = plt.subplots(figsize=(12, 8)) ax.scatter(X[Y==0, 0], X[Y==0, 1], label='Class 0') ax.scatter(X[Y==1, 0], X[Y==1, 1], color='r', label='Class 1') sns.despine(); ax.legend() ax.set(xlabel='X', ylabel='Y', title='Toy binary classification data set');

2、定義貝葉斯神經(jīng)網(wǎng)絡(luò)模型

構(gòu)建2 hidden layers with 5 neurons，權(quán)值用正態(tài)先驗(yàn)分布約束。這里表示的不確定性用先驗(yàn)約束，而預(yù)測(cè)的不確定性用Bernoulli分布。

def construct_nn(ann_input, ann_output):n_hidden = 5# Initialize random weights between each layerinit_1 = np.random.randn(X.shape[1], n_hidden).astype(float)init_2 = np.random.randn(n_hidden, n_hidden).astype(float)init_out = np.random.randn(n_hidden).astype(float)with pm.Model() as neural_network:# Weights from input to hidden layerweights_in_1 = pm.Normal('w_in_1', 0, sd=1, shape=(X.shape[1], n_hidden), testval=init_1)# Weights from 1st to 2nd layerweights_1_2 = pm.Normal('w_1_2', 0, sd=1, shape=(n_hidden, n_hidden), testval=init_2)# Weights from hidden layer to outputweights_2_out = pm.Normal('w_2_out', 0, sd=1, shape=(n_hidden,), testval=init_out)# Build neural-network using tanh activation functionact_1 = pm.math.tanh(pm.math.dot(ann_input,weights_in_1))act_2 = pm.math.tanh(pm.math.dot(act_1, weights_1_2))act_out = pm.math.sigmoid(pm.math.dot(act_2, weights_2_out))# Binary classification -> Bernoulli likelihoodout = pm.Bernoulli('out', act_out,observed=ann_output,total_size=Y_train.shape[0] # IMPORTANT for minibatches)return neural_network# Trick: Turn inputs and outputs into shared variables. # It's still the same thing, but we can later change the values of the shared variable # (to switch in the test-data later) and pymc3 will just use the new data. # Kind-of like a pointer we can redirect. # For more info, see: http://deeplearning.net/software/theano/library/compile/shared.html ann_input = theano.shared(X_train) ann_output = theano.shared(Y_train) neural_network = construct_nn(ann_input, ann_output)

3、變分推斷最優(yōu)化

模型求解可以用MCMC采樣法，如NUTS，但面對(duì)深度網(wǎng)絡(luò)時(shí)，變分推斷更快。

we will use?ADVI?variational inference algorithm which was recently added to?PyMC3, and updated to use the operator variational inference (OPVI) framework. This is much faster and will scale better. Note, that this is a mean-field approximation so we ignore correlations in the posterior.

we can very quickly draw samples from the variational approximation using the?sample?method (this is just sampling from Normal distributions, so not at all the same like MCMC)

lets predict on the hold-out set using a posterior predictive check (PPC).

from pymc3.theanof import set_tt_rng, MRG_RandomStreams set_tt_rng(MRG_RandomStreams(42)) %timewith neural_network:inference = pm.ADVI()approx = pm.fit(n=50000, method=inference) CPU times: user 4 μs, sys: 1e+03 ns, total: 5 μs Wall time: 13.4 μs Average Loss = 128.96: 100%|██████████| 50000/50000 [00:43<00:00, 1138.57it/s] Finished [100%]: Average Loss = 129 trace = approx.sample(draws=5000) plt.plot(-inference.hist) plt.ylabel('ELBO') plt.xlabel('iteration');

# Replace arrays our NN references with the test data ann_input.set_value(X_test) ann_output.set_value(Y_test)with neural_network:ppc = pm.sample_ppc(trace, samples=500, progressbar=False)# Use probability of > 0.5 to assume prediction of class 1 pred = ppc['out'].mean(axis=0) > 0.5 fig, ax = plt.subplots() ax.scatter(X_test[pred==0, 0], X_test[pred==0, 1]) ax.scatter(X_test[pred==1, 0], X_test[pred==1, 1], color='r') sns.despine() ax.set(title='Predicted labels in testing set', xlabel='X', ylabel='Y'); print('Accuracy = {}%'.format((Y_test == pred).mean() * 100))

總結(jié)

以上是生活随笔為你收集整理的概率编程库Pymc3案例之神经网络的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。