Get in Touch
 Duration 21 hours

Course Outline

  1. Distribution in Big Data
    1. Data mining methods (training single-machine + distributed predictions: traditional machine learning algorithms + Mapreduce distributed predictions)
    2. Apache Spark MLlib
  2. Recommendations and Precise Ad Delivery:
    1. Parts of natural language
    2. Text clustering, text classification (labels), synonyms
    3. User profile reconstruction, label system
    4. Strategies for recommendation algorithms
    5. Lift between classes, lift within classes, how to achieve precision
    6. How to build a closed loop for recommendation algorithms
  3. Logistic regression, RankingSVM,
  4. Feature identification: (automatic feature identification in deep learning and graphics)
  5. Natural Language
    1. Chinese word segmentation
    2. Topic models (text clustering)
    3. Text classification
    4. Keyword extraction
    5. Semantic analysis: semantic parser, word2vec to word vectors
    6. RNN Long short-term memory (LSTM) Architecture

Requirements

There are no specific requirements for attending this course.

Testimonials (1)

Related Categories