Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
- Distribution in Big Data
- Data Mining Methods (Training single-machine model + Distributed prediction: Traditional machine learning algorithms + MapReduce distributed prediction)
- Apache Spark MLlib
- Recommendations and Precise Advertising:
- Components of natural language
- Text clustering, text classification (labels), synonyms
- User profile reconstruction, label system
- Strategies for recommendation algorithms
- Inter-class lift, intra-class lift, and how to achieve precision
- How to build a closed loop for recommendation algorithms
- Logistic regression, RankingSVM
- Feature identification: (Automatic feature identification via deep learning and graphics)
- Natural Language
- Chinese word segmentation
- Topic models (text clustering)
- Text classification
- Keyword extraction
- Semantic analysis: semantic parser, word2vec to word vectors
- RNN Long short-term memory (LSTM) Architecture
Requirements
There are no specific prerequisites for attending this course.
21 Hours
Testimonials (1)
This is one of the best hands-on with exercises programming courses I have ever taken.
