Photo OCR (Optical Character Recognition)

Photo OCR: Problem Description and Pipeline

• OCR: Optical Character Recognition

OCR example: Sliding Windows

Artificial data synthesis

Dissussion on getting more data

1. Make sure you have a low bias classifier before expending the effort. (Plot learnign curves) E.g. keep increasing the number of features/number or hidden units neural network until you have a low bias classifier.

2. “How much work would it be to get 10x as much data as we currently have?”

   • Artificial data synthesis

   • Collect / label it yourself

      # 有時候就真的靜下好好 label 一番，
      # 仔細算也不過一兩天(幾小時)的事情，
      # 卻可以讓模型變成好棒棒的兒~ 
      #
      # ex: M = 1,000 筆數
      #     人工 label 一筆 10 秒
      #    總共花 1,000 * 10 秒
     

   • “Croed source” (E.g. Amazon Mechanical Turk)

Ceiling analysis: What part of the pipeline to work on next

Face Recognition Example

Conclusion: Summary and Thank you

我好棒棒阿!!!!!!!!!!!!

Supervise Learning

• Linear regression, logistic regression, neural networks, SVMs

Unsupervised Learning

• K-means, PCA, Anomaly detection

Special applications/special topics

• Recommender systems, large scale machine learning

Advice on building a machine learning system

• Bias/variance, regularization; deciding what to work on next: evaluation of learning algorithms, learning curves, error analysis, ceiling analysis