|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/ml-dl-interviews/
课程评论：没有评论
Coursera 课程：为面试和研究准备的机器学习与深度学习基础 课程概述： 本课程专为对机器学习（ML）和深度学习（DL）感兴趣，并正在为面试或研究做准备的学习者设计。课程旨在提供ML和DL的基础知识，适合初学者、学者、准备面试的学生以及任何希望提升数据科学技能的人。课程将涵盖ML和DL的基础知识，并包含几个案例研究。 本课程将对ML和DL进行广泛介绍，重点讲解探索性数据分析（EDA）和ML模型构建的工具。我们将从Python和ML入门，并通过Keras和Scikit-learn（sklearn）进行案例研究。 课程内容： ### 机器学习 ### 1. **高级统计与机器学习** * 协方差 * 特征值分解 * 主成分分析（PCA） * 中心极限定理 * 高斯分布 * 机器学习的类型 * 参数模型 * 非参数模型 2. **机器学习模型训练** * **监督学习** * 回归 * 分类 * 线性回归 * 梯度下降 * 正规方程 * 局部加权线性回归 * 岭回归 (Ridge Regression) * Lasso 回归 * Scikit-learn 中的其他分类器模型 * Logistic 回归 * 使用线性技术映射非线性函数 * 过拟合与正则化 * 支持向量机 (SVM) * 决策树 * **人工神经网络** * 前向传播 * 反向传播 * 激活函数 * 超参数 * 过拟合 * Dropout * **深度神经网络训练** * 深度神经网络 (DNN) * 卷积神经网络 (CNN) * 循环神经网络 (RNN) (GRU 和 LSTM) * **无监督学习** * 聚类 (k-Means) 3. **实现与案例研究** * Python 与机器学习入门 * 案例研究 - Keras 数字分类器 * 案例研究 - 负荷预测 课程旨在通过清晰的讲解和实践案例，帮助学习者全面掌握机器学习和深度学习的核心概念，从而提升知识水平和职业竞争力。
Interested in Machine Learning, and Deep Learning and preparing for your interviews or research? Then, this course is for you!The course is designed to provide the fundamentals of machine learning and deep learning. It is targeted toward newbies, scholars, students preparing for interviews, or anyone seeking to hone the data science skills necessary. In this course, we will cover the basics of machine learning, and deep learning and cover a few case studies.This short course provides a broad introduction to machine learning, and deep learning. We will present a suite of tools for exploratory data analysis and machine learning modeling. We will get started with python and machine learning and provide case studies using keras and sklearn.### MACHINE LEARNING ###1.) Advanced Statistics and Machine LearningCovarianceEigen Value DecompositionPrincipal Component AnalysisCentral Limit TheoremGaussian DistributionTypes of Machine LearningParametric ModelsNon-parametric Models2.) Training Machine Learning ModelsSupervised Machine LearningRegressionClassificationLinear RegressionGradient DescentNormal EquationsLocally Weighted Linear RegressionRidge RegressionLasso RegressionOther classifier models in sklearnLogistic RegressionMapping non-linear functions using linear techniquesOverfitting and RegularizationSupport Vector MachinesDecision Trees3.) Artificial Neural NetworksForward PropagationBackward PropagationActivation functionsHyperparametersOverfittingDropout4.) Training Deep Neural NetworksDeep Neural NetworksConvolutional Neural NetworksRecurrent Neural Networks (GRU and LSTM)5.) Unsupervised LearningClustering (k-Means)6.) Implementation and Case StudiesGetting started with Python and Machine LearningCase Study - Keras Digit ClassifierCase Study - Load ForecastingSo what are you waiting for? Learn Machine Learning, and Deep Learning in a way that will enhance your knowledge and improve your career!Thanks for joining the course. I am looking forward to seeing you. let's get started!
