Video Lectures of ML by Andrew Ng

[ Video Lectures of ML by Andrew Ng ]

Video LecturesHelp Center

Having trouble viewing lectures? Try changing players. Your current player format is html5. Change to flash.

Lecture Note of Stanford ML

 I. Introduction (Week 1)

  • Welcome (7 min)
  • What is Machine Learning? (7 min)
  • Supervised Learning (12 min)
  • Unsupervised Learning (14 min)

 II. Linear Regression with One Variable (Week 1)

  • Model Representation (8 min)
  • Cost Function (8 min)
  • Cost Function – Intuition I (11 min)
  • Cost Function – Intuition II (9 min)
  • Gradient Descent (11 min)
  • Gradient Descent Intuition (12 min)
  • Gradient Descent For Linear Regression (10 min)
  • What’s Next (6 min)

 III. Linear Algebra Review (Week 1, Optional)

  • Matrices and Vectors (9 min)
  • Addition and Scalar Multiplication (7 min)
  • Matrix Vector Multiplication (14 min)
  • Matrix Matrix Multiplication (11 min)
  • Matrix Multiplication Properties (9 min)
  • Inverse and Transpose (11 min)

 IV. Linear Regression with Multiple Variables (Week 2)

  • Multiple Features (8 min)
  • Gradient Descent for Multiple Variables (5 min)
  • Gradient Descent in Practice I – Feature Scaling (9 min)
  • Gradient Descent in Practice II – Learning Rate (9 min)
  • Features and Polynomial Regression (8 min)
  • Normal Equation (16 min)
  • Normal Equation Noninvertibility (Optional) (6 min)

 V. Octave Tutorial (Week 2)

  • Basic Operations (14 min)
  • Moving Data Around (16 min)
  • Computing on Data (13 min)
  • Plotting Data (10 min)
  • Control Statements: for, while, if statements (13 min)
  • Vectorization (14 min)
  • Working on and Submitting Programming Exercises (4 min)

 VI. Logistic Regression (Week 3)

  • Classification (8 min)
  • Hypothesis Representation (7 min)
  • Decision Boundary (15 min)
  • Cost Function (11 min)
  • Simplified Cost Function and Gradient Descent (10 min)
  • Advanced Optimization (14 min)
  • Multiclass Classification: One-vs-all (6 min)

 VII. Regularization (Week 3)

  • The Problem of Overfitting (10 min)
  • Cost Function (10 min)
  • Regularized Linear Regression (11 min)
  • Regularized Logistic Regression (9 min)

 VIII. Neural Networks: Representation (Week 4)

  • Non-linear Hypotheses (10 min)
  • Neurons and the Brain (8 min)
  • Model Representation I (12 min)
  • Model Representation II (12 min)
  • Examples and Intuitions I (7 min)
  • Examples and Intuitions II (10 min)
  • Multiclass Classification (4 min)

 IX. Neural Networks: Learning (Week 5)

  • Cost Function (7 min)
  • Backpropagation Algorithm (12 min)
  • Backpropagation Intuition (13 min)
  • Implementation Note: Unrolling Parameters (8 min)
  • Gradient Checking (12 min)
  • Random Initialization (7 min)
  • Putting It Together (14 min)
  • Autonomous Driving (7 min)

 X. Advice for Applying Machine Learning (Week 6)

  • Deciding What to Try Next (6 min)
  • Evaluating a Hypothesis (8 min)
  • Model Selection and Train/Validation/Test Sets (12 min)
  • Diagnosing Bias vs. Variance (8 min)
  • Regularization and Bias/Variance (11 min)
  • Learning Curves (12 min)
  • Deciding What to Do Next Revisited (7 min)

 XI. Machine Learning System Design (Week 6)

  • Prioritizing What to Work On (10 min)
  • Error Analysis (13 min)
  • Error Metrics for Skewed Classes (12 min)
  • Trading Off Precision and Recall (14 min)
  • Data For Machine Learning (11 min)

 XII. Support Vector Machines (Week 7)

  • Optimization Objective (15 min)
  • Large Margin Intuition (11 min)
  • Mathematics Behind Large Margin Classification (Optional) (20 min)
  • Kernels I (16 min)
  • Kernels II (16 min)
  • Using An SVM (21 min)

 XIII. Clustering (Week 8)

  • Unsupervised Learning: Introduction (3 min)
  • K-Means Algorithm (13 min)
  • Optimization Objective (7 min)
  • Random Initialization (8 min)
  • Choosing the Number of Clusters (8 min)

 XIV. Dimensionality Reduction (Week 8)

  • Motivation I: Data Compression (10 min)
  • Motivation II: Visualization (6 min)
  • Principal Component Analysis Problem Formulation (9 min)
  • Principal Component Analysis Algorithm (15 min)
  • Choosing the Number of Principal Components (11 min)
  • Reconstruction from Compressed Representation (4 min)
  • Advice for Applying PCA (13 min)

 XV. Anomaly Detection (Week 9)

  • Problem Motivation (8 min)
  • Gaussian Distribution (10 min)
  • Algorithm (12 min)
  • Developing and Evaluating an Anomaly Detection System (13 min)
  • Anomaly Detection vs. Supervised Learning (8 min)
  • Choosing What Features to Use (12 min)
  • Multivariate Gaussian Distribution (Optional) (14 min)
  • Anomaly Detection using the Multivariate Gaussian Distribution (Optional) (14 min)

 XVI. Recommender Systems (Week 9)

  • Problem Formulation (8 min)
  • Content Based Recommendations (15 min)
  • Collaborative Filtering (10 min)
  • Collaborative Filtering Algorithm (9 min)
  • Vectorization: Low Rank Matrix Factorization (8 min)
  • Implementational Detail: Mean Normalization (9 min)

 XVII. Large Scale Machine Learning (Week 10)

  • Learning With Large Datasets (6 min)
  • Stochastic Gradient Descent (13 min)
  • Mini-Batch Gradient Descent (6 min)
  • Stochastic Gradient Descent Convergence (12 min)
  • Online Learning (13 min)
  • Map Reduce and Data Parallelism (14 min)

 XVIII. Application Example: Photo OCR

  • Problem Description and Pipeline (7 min)
  • Sliding Windows (15 min)
  • Getting Lots of Data and Artificial Data (16 min)
  • Ceiling Analysis: What Part of the Pipeline to Work on Next (14 min)

 XIX. Conclusion

 

 

Advertisements

Author: iotmaker

I am interested in IoT, robot, figures & leadership. Also, I have spent almost every day of the past 15 years making robots or electronic inventions or computer programs.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s