Distributed machine learning examples
0 likes770 views
The document discusses distributed machine learning examples such as topic modeling. Topic modeling involves discovering topics from large unstructured document collections and annotating documents with topics. Latent Dirichlet Allocation (LDA) is an unsupervised probabilistic algorithm that can model how documents are generated from topics. Graphical models are used to represent LDA. Real inference with LDA involves fitting a 100-topic LDA model to science journal articles and analyzing the most frequent words in topics and topic proportions of an example article. Topic modeling can be used for text classification and finding patterns in data.
Distributed machine learning examples
- 1. DISTRIBUTED MACHINE LEARNING EXAMPLES STANLEY WANG SOLUTION ARCHITECT, TECH LEAD @SWANG68 http://www.linkedin.com/in/stanley-wang-a2b143b
- 2. Topic Modeling • Topical categorization of blogs, documents or other objects that can be tagged with text, improves the experience for end users; • Discover Sets of Topics from Large Unstructured Collections of documents; • Annotate documents with topic; • Utilize Annotation to Index, Search and Classify on documents;
- 3. The Intuitions behind LDA • Latent Dirichlet Allocation (LDA) is an unsupervised, probabilistic, text clustering algorithm. LDA defines a generative model that can be used to model how documents are generated given a set of topics and the words in the topics;
- 4. Graphical Model for LDA • Topic-based text classification; • Topic modeling can be seen as a pre-processing step before applying supervised learning methods, such as Collaborative Filtering; • Finding patterns in genetic data, images, and social networks;
- 5. Real Inference with LDA • A 100-topic LDA model was fitted to 17,000 articles from the Science journal; • At right are the top 15 most frequent words from the most frequent topics; • At left are the inferred topic proportions for the example article from previous slide;
- 6. Topic Modeling and Analysis
- 8. What is Community Intuition? In social world, community is a collection of users that are more closely related to each other than the rest of the network. The relation between users can be amount of interaction, similar interest, geographical factors etc.
- 9. Why Detect Social Communities? • Behavior Analysis • Location-based Interaction Analysis • Recommender Systems Development • Link Prediction • Customer Interaction and Analysis • Media & Content Analysis • Security • Social Studies
- 13. Metrics of Graph Analysis
- 14. Graph Modularity
- 19. Social Tag Clustering - Examples