|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/introduction-to-machine-learning-in-python/
课程评论：没有评论
课程名称：Python中的机器学习与深度学习训练营 课程概述： 如果您对机器学习和深度学习感兴趣，那么这个课程就是为您准备的！本课程涵盖了机器学习、深度学习、强化学习和机器学习的基本概念。由于这些学习算法可以应用于从软件工程到投资银行等多个领域，因此这些主题在当前非常热门。在每个部分中，我们将讨论这些算法的理论背景，并一起实现相关问题。课程将使用Python及其库SkLearn、Keras和TensorFlow进行实践操作。 ### 课程内容 #### 机器学习部分 - **线性回归**：理解线性回归模型、相关性与协方差矩阵、随机变量之间的线性关系、梯度下降及设计矩阵方法。 - **逻辑回归**：理解逻辑回归、分类算法基础、最大似然函数和估计。 - **K-最近邻分类器**：理解K-最近邻分类器及其非参数算法。 - **朴素贝叶斯算法**：理解朴素贝叶斯算法、基于概率的分类、交叉验证、过拟合与欠拟合。 - **支持向量机（SVM）**：理解支持向量机和支持向量分类器（SVC）、最大边际分类器及核技巧。 - **决策树与随机森林**：决策树分类器、随机森林分类器及组合弱学习者的方法。 - **袋装与提升**：了解袋装和提升的概念、AdaBoost算法及众智结合。 - **聚类算法**：理解聚类算法、K均值聚类和肘部法、DBSCAN算法和层次聚类。 #### 神经网络与深度学习部分 - **前馈神经网络**：单层感知器模型、前馈神经网络、激活函数和反向传播算法。 - **深度神经网络**：了解深度神经网络、ReLU激活函数与梯度消失问题、深度神经网络的训练方法及损失函数。 - **卷积神经网络（CNN）**：理解卷积神经网络、特征选择与核、特征检测、池化与展平。 - **递归神经网络（RNN）**：理解RNN、训练递归神经网络及梯度爆炸问题。 - **长短期记忆（LSTM）与门控循环单元（GRU）**：利用LSTM网络进行时间序列分析。 - **变换器（Transformers）**：词嵌入、查询、键值矩阵、注意力机制及训练变换器。 - **生成对抗网络（GANs）**：理解GANs、生成器与判别器、GAN训练及简单GAN架构的实现。 #### 数值优化和强化学习部分 - **数值优化**：梯度下降算法及其变体、ADAGrad和RMSProp算法、ADAM优化器的理论与实现。 - **强化学习**：马尔可夫决策过程（MDP）、价值迭代与策略迭代、探索与利用问题、多臂老虎机问题、Q学习与深度Q学习，及通过Q学习玩井字棋。 您将获得包括150多节讲座的终身访问权限，以及讲座的幻灯片和源代码！本课程提供30天的退款保证，如果您不满意，将全额退款。 还等什么呢？以一种有趣和实用的方式学习机器学习和深度学习，为您的职业生涯提升和知识增长添砖加瓦！感谢您加入这一课程，让我们开始吧！
Interested in Machine Learning and Deep Learning ? Then this course is for you!This course is about the fundamental concepts of machine learning, deep learning, reinforcement learning and machine learning. These topics are getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking.In each section we will talk about the theoretical background for all of these algorithms then we are going to implement these problems together. We will use Python with SkLearn, Keras and TensorFlow.### MACHINE LEARNING ###Linear Regressionunderstanding linear regression modelcorrelation and covariance matrixlinear relationships between random variablesgradient descent and design matrix approachesLogistic Regressionunderstanding logistic regressionclassification algorithms basicsmaximum likelihood function and estimationK-Nearest Neighbors Classifierwhat is k-nearest neighbour classifier?non-parametric machine learning algorithmsNaive Bayes Algorithmwhat is the naive Bayes algorithm?classification based on probabilitycross-validation overfitting and underfittingSupport Vector Machines (SVMs)support vector machines (SVMs) and support vector classifiers (SVCs)maximum margin classifierkernel trickDecision Trees and Random Forestsdecision tree classifierrandom forest classifiercombining weak learnersBagging and Boostingwhat is bagging and boosting?AdaBoost algorithmcombining weak learners (wisdom of crowds)Clustering Algorithmswhat are clustering algorithms?k-means clustering and the elbow methodDBSCAN algorithmhierarchical clusteringmarket segmentation analysis### NEURAL NETWORKS AND DEEP LEARNING ###Feed-Forward Neural Networks single layer perceptron modelfeed.forward neural networksactivation functionsbackpropagation algorithmDeep Neural Networkswhat are deep neural networks?ReLU activation functions and the vanishing gradient problemtraining deep neural networksloss functions (cost functions)Convolutional Neural Networks (CNNs)what are convolutional neural networks?feature selection with kernelsfeature detectorspooling and flatteningRecurrent Neural Networks (RNNs)what are recurrent neural networks?training recurrent neural networksexploding gradients problemLSTM and GRUstime series analysis with LSTM networksTransformersword embeddingsquery, key and value matricesattention and attention scorestraining a transformerChatGPT and transformersGenerative Adversarial Networks (GANs)what are GANsgenerator and discriminatorhow to train a GANimplementation of a simple GAN architectureNumerical Optimization (in Machine Learning)gradient descent algorithmstochastic gradient descent theory and implementationADAGrad and RMSProp algorithmsADAM optimizer explainedADAM algorithm implementationReinforcement LearningMarkov Decision Processes (MDPs)value iteration and policy iterationexploration vs exploitation problemmulti-armed bandits problemQ learning and deep Q learninglearning tic tac toe with Q learning and deep Q learningYou will get lifetime access to 150+ lectures plus slides and source codes for the lectures! This course comes with a 30 day money back guarantee! If you are not satisfied in any way, you'll get your money back.So what are you waiting for? Learn Machine Learning, Deep Learning in a way that will advance your career and increase your knowledge, all in a fun and practical way!Thanks for joining the course, let's get started!
