吴恩达coursera机器学习

加入官方QQ群：587764486 一起学习打卡！大神在群在线解答！我要报错

简介
目录
详情
点评

简介

标签：
课程分类：热点应用
语言：中文
总时长：18:58:36

吴恩达coursera机器学习文档

扫码关注课程小当家，拉您加入热点应用技术讨论群

00:06:54第1讲 1 - 1 - Welcome (7 min)
00:07:14第2讲 1 - 2 - What is Machine Learning- (7 min)
00:12:29第3讲 1 - 3 - Supervised Learning (12 min)
00:14:13第4讲 1 - 4 - Unsupervised Learning (14 min)
00:08:10第5讲 2 - 1 - Model Representation (8 min)
00:08:12第6讲 2 - 2 - Cost Function (8 min)
00:11:09第7讲 2 - 3 - Cost Function - Intuition I (11 min)
00:08:48第8讲 2 - 4 - Cost Function - Intuition II (9 min)
00:11:30第9讲 2 - 5 - Gradient Descent (11 min)
00:11:50第10讲 2 - 6 - Gradient Descent Intuition (12 min)
00:10:20第11讲 2 - 7 - Gradient Descent For Linear Regression (10 min)
00:05:49第12讲 2 - 8 - What-'s Next (6 min)
00:08:45第13讲 3 - 1 - Matrices and Vectors (9 min)
00:06:53第14讲 3 - 2 - Addition and Scalar Multiplication (7 min)
00:13:39第15讲 3 - 3 - Matrix Vector Multiplication (14 min)
00:11:09第16讲 3 - 4 - Matrix Matrix Multiplication (11 min)
00:09:02第17讲 3 - 5 - Matrix Multiplication Properties (9 min)
00:11:12第18讲 3 - 6 - Inverse and Transpose (11 min)
00:08:22第19讲 4 - 1 - Multiple Features (8 min)
00:05:04第20讲 4 - 2 - Gradient Descent for Multiple Variables (5 min)
00:08:51第21讲 4 - 3 - Gradient Descent in Practice I - Feature Scaling (9 min)
00:07:39第22讲 4 - 5 - Features and Polynomial Regression (8 min)
00:08:58第23讲 4 - 4 - Gradient Descent in Practice II - Learning Rate (9 min)
00:16:17第24讲 4 - 6 - Normal Equation (16 min)
00:05:58第25讲 4 - 7 - Normal Equation Noninvertibility (Optional) (6 min)
00:13:59第26讲 5 - 1 - Basic Operations (14 min)
00:16:07第27讲 5 - 2 - Moving Data Around (16 min)
00:13:14第28讲 5 - 3 - Computing on Data (13 min)
00:09:38第29讲 5 - 4 - Plotting Data (10 min)
00:12:55第30讲 5 - 5 - Control Statements- for, while, if statements (13 min)
00:13:48第31讲 5 - 6 - Vectorization (14 min)
00:03:33第32讲 5 - 7 - Working on and Submitting Programming Exercises (4 min)
00:08:08第33讲 6 - 1 - Classification (8 min)
00:07:24第34讲 6 - 2 - Hypothesis Representation (7 min)
00:14:49第35讲 6 - 3 - Decision Boundary (15 min)
00:11:25第36讲 6 - 4 - Cost Function (11 min)
00:10:14第37讲 6 - 5 - Simplified Cost Function and Gradient Descent (10 min)
00:14:06第38讲 6 - 6 - Advanced Optimization (14 min)
00:06:15第39讲 6 - 7 - Multiclass Classification- One-vs-all (6 min)
00:09:42第40讲 7 - 1 - The Problem of Overfitting (10 min)
00:10:10第41讲 7 - 2 - Cost Function (10 min)
00:10:40第42讲 7 - 3 - Regularized Linear Regression (11 min)
00:08:33第43讲 7 - 4 - Regularized Logistic Regression (9 min)
00:09:36第44讲 8 - 1 - Non-linear Hypotheses (10 min)
00:07:47第45讲 8 - 2 - Neurons and the Brain (8 min)
00:12:01第46讲 8 - 3 - Model Representation I (12 min)
00:11:46第47讲 8 - 4 - Model Representation II (12 min)
00:07:15第48讲 8 - 5 - Examples and Intuitions I (7 min)
00:10:20第49讲 8 - 6 - Examples and Intuitions II (10 min)
00:03:51第50讲 8 - 7 - Multiclass Classification (4 min)
00:06:43第51讲 9 - 1 - Cost Function (7 min)
00:11:59第52讲 9 - 2 - Backpropagation Algorithm (12 min)
00:12:44第53讲 9 - 3 - Backpropagation Intuition (13 min)
00:07:47第54讲 9 - 4 - Implementation Note- Unrolling Parameters (8 min)
00:11:37第55讲 9 - 5 - Gradient Checking (12 min)
00:06:51第56讲 9 - 6 - Random Initialization (7 min)
00:13:23第57讲 9 - 7 - Putting It Together (14 min)
00:06:30第58讲 9 - 8 - Autonomous Driving (7 min)
00:05:50第59讲 10 - 1 - Deciding What to Try Next (6 min)
00:07:35第60讲 10 - 2 - Evaluating a Hypothesis (8 min)
00:12:03第61讲 10 - 3 - Model Selection and Train-Validation-Test Sets (12 min)
00:07:42第62讲 10 - 4 - Diagnosing Bias vs. Variance (8 min)
00:10:47第63讲 10 - 5 - Regularization and Bias-Variance (11 min)
00:11:53第64讲 10 - 6 - Learning Curves (12 min)
00:06:50第65讲 10 - 7 - Deciding What to Do Next Revisited (7 min)
00:09:29第66讲 11 - 1 - Prioritizing What to Work On (10 min)
00:13:11第67讲 11 - 2 - Error Analysis (13 min)
00:11:35第68讲 11 - 3 - Error Metrics for Skewed Classes (12 min)
00:14:05第69讲 11 - 4 - Trading Off Precision and Recall (14 min)
00:11:09第70讲 11 - 5 - Data For Machine Learning (11 min)
00:14:47第71讲 12 - 1 - Optimization Objective (15 min)
00:15:45第72讲 12 - 4 - Kernels I (16 min)
00:15:43第73讲 12 - 5 - Kernels II (16 min)
00:21:03第74讲 12 - 6 - Using An SVM (21 min)
00:03:17第75讲 13 - 1 - Unsupervised Learning- Introduction (3 min)
00:12:33第76讲 13 - 2 - K-Means Algorithm (13 min)
00:07:05第77讲 13 - 3 - Optimization Objective (7 min)
00:07:49第78讲 13 - 4 - Random Initialization (8 min)
00:08:22第79讲 13 - 5 - Choosing the Number of Clusters (8 min)
00:10:10第80讲 14 - 1 - Motivation I- Data Compression (10 min)
00:05:28第81讲 14 - 2 - Motivation II- Visualization (6 min)
00:09:06第82讲 14 - 3 - Principal Component Analysis Problem Formulation (9 min)
00:15:14第83讲 14 - 4 - Principal Component Analysis Algorithm (15 min)
00:10:30第84讲 14 - 5 - Choosing the Number of Principal Components (11 min)
00:03:54第85讲 14 - 6 - Reconstruction from Compressed Representation (4 min)
00:12:49第86讲 14 - 7 - Advice for Applying PCA (13 min)
00:07:38第87讲 15 - 1 - Problem Motivation (8 min)
00:10:28第88讲 15 - 2 - Gaussian Distribution (10 min)
00:12:03第89讲 15 - 3 - Algorithm (12 min)
00:13:08第90讲 15 - 4 - Developing and Evaluating an Anomaly Detection System (13 min)
00:07:36第91讲 15 - 5 - Anomaly Detection vs. Supervised Learning (8 min)
00:12:17第92讲 15 - 6 - Choosing What Features to Use (12 min)
00:13:46第93讲 15 - 7 - Multivariate Gaussian Distribution (Optional) (14 min)
00:14:03第94讲 15 - 8 - Anomaly Detection using the Multivariate Gaussian Distribution (Optional) (14 min)
00:07:55第95讲 16 - 1 - Problem Formulation (8 min)
00:14:32第96讲 16 - 2 - Content Based Recommendations (15 min)
00:10:15第97讲 16 - 3 - Collaborative Filtering (10 min)
00:08:27第98讲 16 - 4 - Collaborative Filtering Algorithm (9 min)
00:08:28第99讲 16 - 5 - Vectorization- Low Rank Matrix Factorization (8 min)
00:08:31第100讲 16 - 6 - Implementational Detail- Mean Normalization (9 min)
00:05:45第101讲 17 - 1 - Learning With Large Datasets (6 min)
00:13:19第102讲 17 - 2 - Stochastic Gradient Descent (13 min)
00:06:18第103讲 17 - 3 - Mini-Batch Gradient Descent (6 min)
00:11:31第104讲 17 - 4 - Stochastic Gradient Descent Convergence (12 min)
00:12:51第105讲 17 - 5 - Online Learning (13 min)
00:14:09第106讲 17 - 6 - Map Reduce and Data Parallelism (14 min)
00:07:02第107讲 18 - 1 - Problem Description and Pipeline (7 min)
00:14:40第108讲 18 - 2 - Sliding Windows (15 min)
00:16:20第109讲 18 - 3 - Getting Lots of Data and Artificial Data (16 min)
00:13:51第110讲 18 - 4 - Ceiling Analysis- What Part of the Pipeline to Work on Next (14 min)
00:04:42第111讲 19 - 1 - Summary and Thank You (5 min)

课程详情

吴恩达是在线教育平台Coursera的联合创始人，吴恩达在2008年发起了“Stanford Engineering Everywhere”（SEE）项目，这个项目把斯坦福的许多课程放到网上，供免费学习。NG也教了一些课程，如机器学习课程，包含了他录制的视频讲座和斯坦福CS299课程的学生材料。

吴恩达的理想是让世界上每个人能够接受高质量的、免费的教育。今天，Coursera和世界上一些顶尖大学的合作者们一起提供高质量的免费在线课程。Coursera是世界上最大的MOOC平台。

点评

讲师简介

吴恩达

吴恩达（1976-，英文名：Andrew Ng），华裔美国人，是斯坦福大学计算机科学系和电子工程系副教授，人工智能实验室主任。吴恩达是人工智能和机器学习领域国际上最权威的学者之一。吴恩达也是在线教育平台Coursera的联合创始人（with Daphne Koller）。

排行榜

最近一周
最近三月
最近一年

查看更多排行榜

吴恩达coursera机器学习

简介

目录

课程详情

点评

讲师简介

排行榜

最新学习