                        課程
                    
                        /后端開發(fā)
                        
                            /Python
                        
                        /機(jī)器學(xué)習(xí)-實(shí)現(xiàn)簡單神經(jīng)網(wǎng)絡(luò)

缺少的那一節(jié)

我用的python3.7，調(diào)整了視頻中的錯(cuò)誤，函數(shù)的位置和命名問題，但是出現(xiàn)TypeError: can't multiply sequence by non-int of type 'float'這個(gè)錯(cuò)誤，python3中不能這么寫嗎，以下為我的感知器類代碼

import numpy as np
class Perception(object):
??? '''
??? eta:學(xué)習(xí)率
??? n_iter：權(quán)重向量的訓(xùn)練次數(shù)
??? w_:神經(jīng)分叉權(quán)重向量
??? error_:記錄神經(jīng)元判斷出錯(cuò)次數(shù)
??? '''
??? def __init__(self,eta = 0.01,n_iter = 10):
??????? self.eta = eta
??????? self.n_iter = n_iter
??????? pass
??? def fit(self,x,y):
??????? '''
??????? 輸入訓(xùn)練數(shù)據(jù)，訓(xùn)練神經(jīng)元,x輸入樣本向量，y對(duì)應(yīng)樣本分類
??????? x:shape(n_samples,n_features)
??????? n_samples:樣本量
??????? n_feature:神經(jīng)元分叉數(shù)量
??????? 例：x:[[1,2,3],[4,5,6]]
??????? n_samples:2
??????? n_feature:3
??????? y:[1,-1]
??????? '''
??????? '''
??????? 初始化權(quán)重向量為0
??????? 加一是因?yàn)閷⑶懊嫠惴ㄌ岬降膚0,也就是步調(diào)函數(shù)閾值
??????? w_:權(quán)重向量
??????? error_:錯(cuò)誤記錄向量
??????? '''
??????? self.errors_ = []
??????? self.w_ = np.zeros(1 + x.shape[1])
??????? for _ in range(self.n_iter):
??????????? errors = 0
??????????? for xi,target in zip(x,y):
??????????????? '''
??????????????? zip(x,y):[[1,2,3,1],[4,5,6,-1]]
??????????????? '''
??????????????? update = (self.eta) * (target - self.predict(xi))
??????????????? self.w_[1:] += update * xi
??????????????? self.w_[0] += update
??????????????? '''
??????????????? ▽w(n) = update * x[n]
??????????????? '''
??????????????? errors += int(update != 0.0)
??????????????? self.errors_.append(errors)
??????????????? pass
??????????? pass
??? def net_input(self,x):
??????? '''
??????? z = w0 * 1 + w1 * x1 +... +wn * xn
??????? '''
??????? z = np.dot(x,self.w_[1:]) + self.w_[0]
??????? return z
??????? pass
??? def predict(self,x):
??????? return np.where(self.net_input(x)>=0.0,1,-1)
??????? pass

石明昊

2019-11-20

源自：機(jī)器學(xué)習(xí)-實(shí)現(xiàn)簡單神經(jīng)網(wǎng)絡(luò) 3-5

關(guān)注問題我要回答

1121

操作

收起

1 回答

Du1in9
2020-07-20

我也用的python3.7，這是我的代碼，謝謝采納~

import?numpy?as?np

class?Perceptron(object):
????#?注釋1
????def?__init__(self,?eta?=?0.01,?n_iter?=?10):
????????self.eta?=?eta
????????self.n_iter?=?n_iter
????def?fit(self,?X,?y):
????????#?注釋2
????????self.w_?=?np.zeros(1?+?X.shape[1])
????????self.errors_?=?[]
????????for?_?in?range(self.n_iter):
????????????errors?=?0
????????????#?注釋3
????????????for?xi,?target?in?zip(X,?y):
????????????????update?=?self.eta?*?(target?-?self.predict(xi))
????????????????#?注釋4
????????????????self.w_[1:]?+=?update?*?xi
????????????????self.w_[0]?+=?update
????????????????errors?+=?int(update?!=?0.0)
????????????????self.errors_.append(errors)
????def?net_input(self,?X):
????????#?注釋5
????????return?np.dot(X,?self.w_[1:])?+?self.w_[0]
????def?predict(self,?X):
????????return?np.where(self.net_input(X)?>=?0.0,?1,?-1)

注釋1：
????eta：學(xué)習(xí)率
????n_iter：權(quán)重向量的訓(xùn)練次數(shù)
????w_：神經(jīng)分叉權(quán)重向量
????errors_：用于記錄神經(jīng)元判斷出錯(cuò)次數(shù)
注釋2：
????輸入訓(xùn)練數(shù)據(jù)，培訓(xùn)神經(jīng)元，X是輸入樣本向量，y是對(duì)應(yīng)的樣本分類
????X:shape[n_samples,?n_features]
????比如：X:[[1,?2,?3],?[4,?5,?6]]
????那么：n_samples:?2，n_features:?3，y:[1,?-1]

????初始化權(quán)重向量為0，加1是因?yàn)樘岬降膚0,即步調(diào)函數(shù)的閾值
注釋3：
????比如：X:[[1,?2,?3],?[4,?5,?6]
????所以y:[1,?-1]，zip(X,?y):[[1,?2,?3,?1].?[4,?5,?6,?-1]]

????update?=?n?*?(y?-?y')
注釋4：
????xi是一個(gè)向量
????update?*?xi等價(jià)于：[?w1?=?x1*update,?w2?=?x2*update,?...]
注釋5：
????z?=?w0*1?+?w1*x1?+?w2*x2?+?...?
????np.dot()是做點(diǎn)積