パーセプトロンとの違いは、重みの更新方法
目的関数(Objective function) ... 学習過程で最適化される関数。多くの場合は コスト関数 (cost function)
誤差平方和(Sum of Squared Error:SSE) $$ J(w) = \frac{1}{2}\sum_i(y^{(i)}-\phi(z^{(i)}))^2 $$
利点
コスト関数$ J(w) $の勾配$ \nabla J(w) $に沿って1ステップ進む $$ w := w + \Delta w $$ 重みの変化である$ \Delta w $は、負の勾配に学習率$ \eta $を掛けたもの $$ \Delta w = -\eta\nabla J(w) $$
In [1]:
class AdalineGD(object):
"""ADAptive LInear NEuron classifier.
Parameters
------------
eta : float
Learning rate (between 0.0 and 1.0)
n_iter : int
Passes over the training dataset.
Attributes
-----------
w_ : 1d-array
Weights after fitting.
cost_ : list
Sum-of-squares cost function value in each epoch.
"""
def __init__(self, eta=0.01, n_iter=50):
self.eta = eta
self.n_iter = n_iter
def fit(self, X, y):
""" Fit training data.
Parameters
----------
X : {array-like}, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples and
n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : object
"""
self.w_ = np.zeros(1 + X.shape[1])
self.cost_ = []
for i in range(self.n_iter):
net_input = self.net_input(X)
# Please note that the "activation" method has no effect
# in the code since it is simply an identity function. We
# could write `output = self.net_input(X)` directly instead.
# The purpose of the activation is more conceptual, i.e.,
# in the case of logistic regression, we could change it to
# a sigmoid function to implement a logistic regression classifier.
output = self.activation(X)
errors = (y - output)
self.w_[1:] += self.eta * X.T.dot(errors)
self.w_[0] += self.eta * errors.sum()
cost = (errors**2).sum() / 2.0
self.cost_.append(cost)
return self
def net_input(self, X):
"""Calculate net input"""
return np.dot(X, self.w_[1:]) + self.w_[0]
def activation(self, X):
"""Compute linear activation"""
return self.net_input(X)
def predict(self, X):
"""Return class label after unit step"""
return np.where(self.activation(X) >= 0.0, 1, -1)
In [4]:
import pandas as pd
df = pd.read_csv('https://archive.ics.uci.edu/ml/'
'machine-learning-databases/iris/iris.data', header=None)
import matplotlib.pyplot as plt
import numpy as np
# select setosa and versicolor
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
# extract sepal length and petal length
X = df.iloc[0:100, [0, 2]].values
fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(8, 4))
ada1 = AdalineGD(n_iter=10, eta=0.01).fit(X, y)
ax[0].plot(range(1, len(ada1.cost_) + 1), np.log10(ada1.cost_), marker='o')
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('log(Sum-squared-error)')
ax[0].set_title('Adaline - Learning rate 0.01')
ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y)
ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Sum-squared-error')
ax[1].set_title('Adaline - Learning rate 0.0001')
plt.tight_layout()
# plt.savefig('./adaline_1.png', dpi=300)
plt.show()
In [6]:
from matplotlib.colors import ListedColormap
def plot_decision_regions(X, y, classifier, resolution=0.02):
# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],
alpha=0.8, c=cmap(idx),
edgecolor='black',
marker=markers[idx],
label=cl)
In [7]:
# standardize features
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()
ada = AdalineGD(n_iter=15, eta=0.01)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Gradient Descent')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
# plt.savefig('./adaline_2.png', dpi=300)
plt.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.tight_layout()
# plt.savefig('./adaline_3.png', dpi=300)
plt.show()
In [ ]: