guoguanglu/andrew-ng_machine-learning

my note about the Andrew-Ng's machine learning videos

Andrew-Ng Machine Learning Notes

This is my note on Andrew-Ng's machining learning. Thank you for asking questions.

---

• Author: Guo Guanglu
• E-mail: [email protected]
• QQ: 2360889142

---

Back to github.io

---

Content

• The first week content
  • What is the machine learning
    • Supervised learning
    • Unsupervised learning
  • Model and cost function
    • Model representation
    • Cost function
  • Parameter Learning
    • Gradient descent
    • Gradient descent intuiton
    • gradient descent for linear regression
• The second week content
  • Multivariate Linear
    • Multiple features
    • Gradient descent for multiple variables
    • Gradient descent in practice I - feaure scaling
    • Gradient descent in practice II - learning rate
    • Features and polynomial regression
  • Computing parameters analytically
    • Normal equation
    • Normal equation noninvertibility
  • Submitting programming assignments
    • Working on and Submitting programming assignments
• The third week content
  • Classification and representation
    • Classification
    • Hypothesis representation
    • Decision boundary
  • Logistic regression model
    • Cost function
    • Simplified cost function and gradient descent
    • Advanced optimization
  • Multiclass classification
    • Multiclass classification:One-vs-all
  • Solving the problem of overfitting
    • The problem of overfitting
    • Cost function
    • Regularized linear regression
    • Regularized logistic regression
• The fourth week content
  • Neural networks
    • Model representation I
    • Model representation II
  • Applications
    • Examples and intuitions I
    • Examples and intuitions II
    • Multiclass classification
• The fifth week content
  • Cost function and backpropagation
    • Cost function
    • Backpropagation algorithm
    • Backpropagation intuition
  • Backpropagation in practice
    • Implementation note: unrolling parameters
    • Gradient checking
    • Random initialization
    • Putting it together
• The sixth week content
  • Evaluating a learning algorithm
    • Evaluatinng a hypothesis
    • Model selection and Train/Validation/Test Sets
  • Bias vs. variance
    • Diagnosing Bias vs. variance
    • Regularization and bias/variance
    • Learning curves
    • Deciding what to do next revisited
  • Building a spam classifier
    • prioritizing what to work on
    • Error analysis
  • Using large data sets
    • Data for machine learning
• The seventh week content
  • Large margin classification
    • Optimization objective
    • Large margin intuition
    • Mathematics behind large margin classification
  • Kernels
    • Kernels I
    • Kernels II
  • SVM in practice
    • Using an SVM
• The eighth week content
  • Clustring
    • K-means algorithm
    • Optimization objective
    • Random initialization
    • Choosing the number of clusters
  • Motivation
    • Motivation I: data compression
    • Motivation II: visualization
  • Principal component analysis
    • Principal component analysis problem formulation
    • Principal component analysis algorithm
  • Applying PCA
    • Reconstruction from compressed representation
    • Choosing the number of principal components
    • Advice for applying PCA
• The ninth week content
  • Density estimation
    • Problem motivation
    • Gaussian distribution
    • Algorithm
  • Building an anomaly detection system
    • Developing and evaluating an anomaly detection system
    • Anomaly detection vs supervised learning
    • Choosing what features to use
  • Multivariate Gaussian distribution
    • Multivariate Gaussian distribution
    • Anomaly detection using the multivariate Gaussian distribution
  • Predicting movie ratings
    • Problem formulation
    • Content based recommendations
  • Collaborative filtering
    • Collaborative filtering
    • Collaborative filtering algorithm
  • Low rank matrix factroization
    • Vectrization: low rank matrix factroization
    • Implementational detiail: mean normalization
• The tenth week
  • Gradient descent with large datasets
    • Learning with large datasets
    • Stochastic gradient descent
    • Mini batch gradient descent
    • Stochastic gradient descent
  • Advanced topics
    • Online learning
    • Map reduce and data parallelism
• The eleventh week
  • Photo OCR
    • Problem description and pipeline
    • Sliding windwos
    • Getting lots of data and artificial data
    • Ceiling analysis: what part of the pipeline to work on next
  • Conclusion

---

Reference

https://www.coursera.org/learn/machine-learning/lecture/db3jS/model-representation

---