您好,登錄后才能下訂單哦!
本篇內(nèi)容介紹了“python人工智能算法之人工神經(jīng)網(wǎng)絡(luò)怎么使用”的有關(guān)知識(shí),在實(shí)際案例的操作過(guò)程中,不少人都會(huì)遇到這樣的困境,接下來(lái)就讓小編帶領(lǐng)大家學(xué)習(xí)一下如何處理這些情況吧!希望大家仔細(xì)閱讀,能夠?qū)W有所成!
(Artificial Neural Network,ANN)是一種模仿生物神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)和功能的數(shù)學(xué)模型,其目的是通過(guò)學(xué)習(xí)和訓(xùn)練,在處理未知的輸入數(shù)據(jù)時(shí)能夠進(jìn)行復(fù)雜的非線性映射關(guān)系,實(shí)現(xiàn)自適應(yīng)的智能決策??梢哉f(shuō),ANN是人工智能算法中最基礎(chǔ)、最核心的一種算法。
ANN模型的基本結(jié)構(gòu)包含輸入層、隱藏層和輸出層。輸入層接收輸入數(shù)據(jù),隱藏層負(fù)責(zé)對(duì)數(shù)據(jù)進(jìn)行多層次、高維度的變換和處理,輸出層對(duì)處理后的數(shù)據(jù)進(jìn)行輸出。ANN的訓(xùn)練過(guò)程是通過(guò)多次迭代,不斷調(diào)整神經(jīng)網(wǎng)絡(luò)中各層的權(quán)重,從而使得神經(jīng)網(wǎng)絡(luò)能夠?qū)斎霐?shù)據(jù)進(jìn)行正確的預(yù)測(cè)和分類。
接下來(lái)看看一個(gè)簡(jiǎn)單的人工神經(jīng)網(wǎng)絡(luò)算法示例:
import numpy as np class NeuralNetwork(): def __init__(self, layers): """ layers: 數(shù)組,包含每個(gè)層的神經(jīng)元數(shù)量,例如 [2, 3, 1] 表示 3 層神經(jīng)網(wǎng)絡(luò),第一層 2 個(gè)神經(jīng)元,第二層 3 個(gè)神經(jīng)元,第三層 1 個(gè)神經(jīng)元。 weights: 數(shù)組,包含每個(gè)連接的權(quán)重矩陣,默認(rèn)值隨機(jī)生成。 biases: 數(shù)組,包含每個(gè)層的偏差值,默認(rèn)值為 0。 """ self.layers = layers self.weights = [np.random.randn(a, b) for a, b in zip(layers[1:], layers[:-1])] self.biases = [np.zeros((a, 1)) for a in layers[1:]] def sigmoid(self, z): """Sigmoid 激活函數(shù).""" return 1 / (1 + np.exp(-z)) def forward_propagation(self, a): """前向傳播.""" for w, b in zip(self.weights, self.biases): z = np.dot(w, a) + b a = self.sigmoid(z) return a def backward_propagation(self, x, y): """反向傳播.""" nabla_w = [np.zeros(w.shape) for w in self.weights] nabla_b = [np.zeros(b.shape) for b in self.biases] a = x activations = [x] zs = [] for w, b in zip(self.weights, self.biases): z = np.dot(w, a) + b zs.append(z) a = self.sigmoid(z) activations.append(a) delta = self.cost_derivative(activations[-1], y) * self.sigmoid_prime(zs[-1]) nabla_b[-1] = delta nabla_w[-1] = np.dot(delta, activations[-2].transpose()) for l in range(2, len(self.layers)): z = zs[-l] sp = self.sigmoid_prime(z) delta = np.dot(self.weights[-l+1].transpose(), delta) * sp nabla_b[-l] = delta nabla_w[-l] = np.dot(delta, activations[-l-1].transpose()) return (nabla_w, nabla_b) def train(self, x_train, y_train, epochs, learning_rate): """訓(xùn)練網(wǎng)絡(luò).""" for epoch in range(epochs): nabla_w = [np.zeros(w.shape) for w in self.weights] nabla_b = [np.zeros(b.shape) for b in self.biases] for x, y in zip(x_train, y_train): delta_nabla_w, delta_nabla_b = self.backward_propagation(np.array([x]).transpose(), np.array([y]).transpose()) nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)] nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)] self.weights = [w-(learning_rate/len(x_train))*nw for w, nw in zip(self.weights, nabla_w)] self.biases = [b-(learning_rate/len(x_train))*nb for b, nb in zip(self.biases, nabla_b)] def predict(self, x_test): """預(yù)測(cè).""" y_predictions = [] for x in x_test: y_predictions.append(self.forward_propagation(np.array([x]).transpose())[0][0]) return y_predictions def cost_derivative(self, output_activations, y): """損失函數(shù)的導(dǎo)數(shù).""" return output_activations - y def sigmoid_prime(self, z): """Sigmoid 函數(shù)的導(dǎo)數(shù).""" return self.sigmoid(z) * (1 - self.sigmoid(z))
使用以下代碼示例來(lái)實(shí)例化和使用這個(gè)簡(jiǎn)單的神經(jīng)網(wǎng)絡(luò)類:
x_train = [[0, 0], [1, 0], [0, 1], [1, 1]] y_train = [0, 1, 1, 0] # 創(chuàng)建神經(jīng)網(wǎng)絡(luò) nn = NeuralNetwork([2, 3, 1]) # 訓(xùn)練神經(jīng)網(wǎng)絡(luò) nn.train(x_train, y_train, 10000, 0.1) # 測(cè)試神經(jīng)網(wǎng)絡(luò) x_test = [[0, 0], [1, 0], [0, 1], [1, 1]] y_test = [0, 1, 1, 0] y_predictions = nn.predict(x_test) print("Predictions:", y_predictions) print("Actual:", y_test)
輸出結(jié)果:
Predictions: [0.011602156431658403, 0.9852717774725432, 0.9839448924887225, 0.020026540429992387]
Actual: [0, 1, 1, 0]
“python人工智能算法之人工神經(jīng)網(wǎng)絡(luò)怎么使用”的內(nèi)容就介紹到這里了,感謝大家的閱讀。如果想了解更多行業(yè)相關(guān)的知識(shí)可以關(guān)注億速云網(wǎng)站,小編將為大家輸出更多高質(zhì)量的實(shí)用文章!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如果涉及侵權(quán)請(qǐng)聯(lián)系站長(zhǎng)郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。