{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "* 课程名称：Machine Learning\n", "* 课程来源：https://www.coursera.org/\n", "* 课程地址：https://www.coursera.org/learn/machine-learning\n", "* 讲师：Andrew Ng\n", "\n", "## Week 1\n", "\n", "### Introduction\n", "\n", "#### Welcome to Machine Learning!\n", "#### Welcome\n", "#### What is Machine Learning?\n", "#### Supervised Learning\n", "#### Unsupervised Learning\n", "\n", "### Linear Regression with One Variable\n", "\n", "#### Model Representation\n", "#### Cost Function\n", "#### Cost Function - Intuition I\n", "#### Cost Function - Intuition II\n", "#### Gradient Descent\n", "#### Gradient Descent Intuition\n", "#### Gradient Descent For Linear Regression\n", "\n", "### Linear Algebra Review\n", "\n", "#### Matrices and Vectors\n", "#### Addition and Scalar Multiplication\n", "#### Matrix Vector Multiplication\n", "#### Matrix Matrix Multiplication\n", "#### Matrix Multiplication Properties\n", "#### Inverse and Transpose\n", "\n", "## Week 2\n", "\n", "### Linear Regression with Multiple Variables\n", "\n", "#### Multiple Features\n", "#### Gradient Descent for Multiple Variables\n", "#### Gradient Descent in Practice I - Feature Scaling\n", "#### Gradient Descent in Practice II - Learning Rate\n", "#### Features and Polynomial Regression\n", "#### Normal Equation\n", "#### Normal Equation Noninvertibility\n", "#### Working on and Submitting Programming Assignments\n", "\n", "### Octave/Matlab Tutorial\n", "\n", "#### Basic Operations\n", "#### Moving Data Around\n", "#### Computing on Data\n", "#### Plotting Data\n", "#### Control Statements: for, while, if statement\n", "#### Vectorization\n", "\n", "## Week 3\n", "\n", "### Logistic Regression\n", "\n", "#### Classification\n", "#### Hypothesis Representation\n", "#### Decision Boundary\n", "#### Cost Function\n", "#### Simplified Cost Function and Gradient Descent\n", "#### Advanced Optimization\n", "#### Multiclass Classification: One-vs-all\n", "\n", "### Regularization\n", "\n", "#### The Problem of Overfitting\n", "#### Cost Function\n", "#### Regularized Linear Regression\n", "#### Regularized Logistic Regression\n", "\n", "## Week 4\n", "\n", "### Neural Networks: Representation\n", "\n", "#### Non-linear Hypotheses\n", "#### Neurons and the Brain\n", "#### Model Representation I\n", "#### Model Representation II\n", "#### Examples and Intuitions I\n", "#### Examples and Intuitions II\n", "#### Multiclass Classification\n", "\n", "## Week 5\n", "\n", "### Neural Networks: Learning\n", "\n", "#### Cost Function\n", "#### Backpropagation Algorithm\n", "#### Backpropagation Intuition\n", "#### Implementation Note: Unrolling Parameters\n", "#### Gradient Checking\n", "#### Random Initialization\n", "#### Putting It Together\n", "#### Autonomous Driving\n", "\n", "## Week 6\n", "\n", "### Advice for Applying Machine Learning\n", "\n", "#### Deciding What to Try Next\n", "#### Evaluating a Hypothesis\n", "#### Model Selection and Train/Validation/Test Sets\n", "#### Diagnosing Bias vs. Variance\n", "#### Regularization and Bias/Variance\n", "#### Learning Curves\n", "#### Deciding What to Do Next Revisited\n", "\n", "### Machine Learning System Design\n", "\n", "#### Prioritizing What to Work On\n", "#### Error Analysis\n", "#### Error Metrics for Skewed Classes\n", "#### Trading Off Precision and Recall\n", "#### Data For Machine Learning\n", "\n", "## Week 7\n", "\n", "### Support Vector Machines\n", "\n", "#### Optimization Objective\n", "#### Large Margin Intuition\n", "#### Mathematics Behind Large Margin Classification\n", "#### Kernels I\n", "#### Kernels II\n", "#### Using An SVM\n", "\n", "## Week 8\n", "\n", "### Unsupervised Learning\n", "\n", "#### Unsupervised Learning: Introduction\n", "#### K-Means Algorithm\n", "#### Optimization Objective\n", "#### Random Initialization\n", "#### Choosing the Number of Clusters\n", "\n", "### Dimensionality Reduction\n", "\n", "#### Motivation I: Data Compression\n", "#### Motivation II: Visualization\n", "#### Principal Component Analysis Problem Formulation\n", "#### Principal Component Analysis Algorithm\n", "#### Reconstruction from Compressed Representation\n", "#### Choosing the Number of Principal Components\n", "#### Advice for Applying PCA\n", "\n", "## Week 9\n", "\n", "### Anomaly Detection\n", "\n", "#### Problem Motivation\n", "#### Gaussian Distribution\n", "#### Algorithm\n", "#### Developing and Evaluating an Anomaly Detection System\n", "#### Anomaly Detection vs. Supervised Learning\n", "#### Choosing What Features to Use\n", "#### Multivariate Gaussian Distribution\n", "#### Anomaly Detection using the Multivariate Gaussian Distribution\n", "\n", "### Recommender Systems\n", "\n", "#### Problem Formulation\n", "#### Content Based Recommendations\n", "#### Collaborative Filtering\n", "#### Collaborative Filtering Algorithm\n", "#### Vectorization: Low Rank Matrix Factorization\n", "#### Implementational Detail: Mean Normalization\n", "\n", "## Week 10\n", "\n", "### Large Scale Machine Learning\n", "\n", "#### Learning With Large Datasets\n", "#### Stochastic Gradient Descent\n", "#### Mini-Batch Gradient Descent\n", "#### Stochastic Gradient Descent Convergence\n", "#### Online Learning\n", "#### Map Reduce and Data Parallelism\n", "\n", "## Week 11\n", "\n", "### Application Example: Photo OCR\n", "\n", "#### Problem Description and Pipeline\n", "#### Sliding Windows\n", "#### Getting Lots of Data and Artificial Data\n", "#### Ceiling Analysis: What Part of the Pipeline to Work on Next\n", "#### Summary and Thank You" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.1" } }, "nbformat": 4, "nbformat_minor": 2 }