斯坦福大学吴恩达Andrew Ng机器学习教程,全套视频教程学习资料通过百度云网盘下载

admin

资源详情



机器学习是一门让计算机在非精确编程下進行活动的科学。在过去十年，机器学习促成了无人驾驶车、高效语音识别、精确网络搜索及人类基因组认知的大力发展。机器学习如此无孔不入，你可能已经在不知情的情况下利用过无数次。许多研究者认为，这种手段是达到人类水平AI的最佳方式。这门课程中，你将学习到高效的机器学习技巧，及学会如何利用它为你服务。重点是，你不仅能学到理论基础，更能知晓如何快速有效应用这些技巧到新的问题上。最后，你会接触到硅谷创新中几个优秀的涉及机器学习与AI的应用实例。
此课程将广泛介绍机器学习、数据挖掘与统计模式识别的知识。
主题包括：
(i)监督学习（参数/非参数算法、支持向量机、内核、神经网络）。
(iii)机器学习的优秀案例（偏差/方差理论；机器学习和人工智能的创新过程）课程将拮取案例研究与应用，学习如何将学习算法应用到智能机器人（观感，控制）、文字理解（网页搜索，防垃圾邮件）、计算机视觉、医学信息学、音频、数据挖掘及其他领域上。


【课程内容】
1-1-Welcome(7min)
1-2-WhatisMachineLearning-(7min)
1-3-SupervisedLearning(12min)
1-4-UnsupervisedLearning(14min)
2-1-ModelRepresentation(8min)
2-2-CostFunction(8min)
2-3-CostFunction-IntuitionI(11min)
2-4-CostFunction-IntuitionII(9min)
2-5-GradientDescent(11min)
2-6-GradientDescentIntuition(12min)
2-7-GradientDescentForLinearRegression(10min)
2-8-What-'sNext(6min)
3-1-MatricesandVectors(9min)
3-2-AdditionandScalarMultiplication(7min)
3-3-MatrixVectorMultiplication(14min)
3-4-MatrixMatrixMultiplication(11min)
3-5-MatrixMultiplicationProperties(9min)
3-6-InverseandTranspose(11min)
4-1-MultipleFeatures(8min)
4-2-GradientDescentforMultipleVariables(5min)
4-3-GradientDescentinPracticeI-FeatureScaling(9min)
4-4-GradientDescentinPracticeII-LearningRate(9min)
4-5-FeaturesandPolynomialRegression(8min)
4-6-NormalEquation(16min)
4-7-NormalEquationNoninvertibility(Optional)(6min)
5-1-BasicOperations(14min)
5-2-MovingDataAround(16min)
5-3-ComputingonData(13min)
5-4-PlottingData(10min)
5-5-ControlStatements-for,while,ifstatements(13min)
5-6-Vectorization(14min)
5-7-WorkingonandSubmittingProgrammingExercises(4min)
6-1-Classification(8min)
6-2-HypothesisRepresentation(7min)
6-3-DecisionBoundary(15min)
6-4-CostFunction(11min)
6-5-SimplifiedCostFunctionandGradientDescent(10min)
6-6-AdvancedOptimization(14min)
6-7-MulticlassClassification-One-vs-all(6min)
7-1-TheProblemofOverfitting(10min)
7-2-CostFunction(10min)
7-3-RegularizedLinearRegression(11min)
7-4-RegularizedLogisticRegression(9min)
8-1-Non-linearHypotheses(10min)
8-2-NeuronsandtheBrain(8min)
8-3-ModelRepresentationI(12min)
8-4-ModelRepresentationII(12min)
8-5-ExamplesandIntuitionsI(7min)
8-6-ExamplesandIntuitionsII(10min)
8-7-MulticlassClassification(4min)
9-1-CostFunction(7min)
9-2-BackpropagationAlgorithm(12min)
9-3-BackpropagationIntuition(13min)
9-4-ImplementationNote-UnrollingParameters(8min)
9-5-GradientChecking(12min)
9-6-RandomInitialization(7min)
9-7-PuttingItTogether(14min)
9-8-AutonomousDriving(7min)
10-1-DecidingWhattoTryNext(6min)
10-2-EvaluatingaHypothesis(8min)
10-3-ModelSelectionandTrain-Validation-TestSets(12min)
10-4-DiagnosingBiasvs.Variance(8min)
10-5-RegularizationandBias-Variance(11min)
10-6-LearningCurves(12min)
10-7-DecidingWhattoDoNextRevisited(7min)
11-1-PrioritizingWhattoWorkOn(10min)
11-2-ErrorAnalysis(13min)
11-3-ErrorMetricsforSkewedClasses(12min)
11-4-TradingOffPrecisionandRecall(14min)
11-5-DataForMachineLearning(11min)
12-1-OptimizationObjective(15min)
12-2-LargeMarginIntuition(11min)
12-3-MathematicsBehindLargeMarginClassification(Optional)(20min)
12-4-KernelsI(16min)
12-5-KernelsII(16min)
12-6-UsingAnSVM(21min)
13-1-UnsupervisedLearning-Introduction(3min)
13-2-K-MeansAlgorithm(13min)
13-3-OptimizationObjective(7min)
13-4-RandomInitialization(8min)
13-5-ChoosingtheNumberofClusters(8min)
14-1-MotivationI-DataCompression(10min)
14-2-MotivationII-Visualization(6min)
14-3-PrincipalComponentAnalysisProblemFormulation(9min)
14-4-PrincipalComponentAnalysisAlgorithm(15min)
14-5-ChoosingtheNumberofPrincipalComponents(11min)
14-6-ReconstructionfromCompressedRepresentation(4min)
14-7-AdviceforApplyingPCA(13min)
15-1-ProblemMotivation(8min)
15-2-GaussianDistribution(10min)
15-3-Algorithm(12min)
15-4-DevelopingandEvaluatinganAnomalyDetectionSystem(13min)
15-5-AnomalyDetectionvs.SupervisedLearning(8min)
15-6-ChoosingWhatFeaturestoUse(12min)<brstyle="overflow-wrap:break-word;color:rgb(111,116,121);font-family:-apple-system,"helvetica=""neue",=""helvetica,=""arial,="""pingfang=""sc",="""hiragino=""sans=""gb",=""stheiti,="""microsoft=""yahei",=""jhenghei",=""simsun,=""sans-serif;=""font-size:=""14px;"="">

游客，如果您要查看本帖隐藏内容请回复