Combinatorial Approach to Data Mining [1/9]

Channel:
Microsoft Research
Subscribers:
349,000
Published on ● Video Link: https://www.youtube.com/watch?v=p1qN3_rXYBI


Duration: 58:11
78 views
1

In many algorithmic problems like nearest neighbor search, clustering, near-duplicate detection or decentralized navigation input dataset is described either by some explicit representation (e.g. vectors) or by oracle access to pairwise distances. In this talk we assume that our knowledge about dataset is much more limited. All informaton provided to an algorithm has the form A



Other Videos By Microsoft Research


2016-09-06Vinegar: Leading Indicators in Query Logs
2016-09-06The Truth is Out There: Aggregating Answers from Multiple Web Sources
2016-09-06Bringing the Social Component to the Web
2016-09-06Statistical Machine Learning for Users Modelling
2016-09-06Incorporating Trust into Web Authority
2016-09-06Mine Query/Click Log for Collaborative Internet Search
2016-09-06Combining Econometric and Text Mining Approaches for Measuring Online Information Exchange
2016-09-06Heap assertions on demand
2016-09-06Stacked Graphical Learning for Text Mining
2016-09-06Entity and Relation Types in Web Search: Annotation, Indexing and Scoring Techniques
2016-09-06Combinatorial Approach to Data Mining [1/9]
2016-09-06Learning using Large Datasets
2016-09-06Locating Family Values: A Field Trial of the Whereabouts Clock
2016-09-06VISP: Visualizing Information Search Processes
2016-09-06Dynamics, Emergence and Simulation
2016-09-06User Intention and Interaction for Improving Search Effectiveness
2016-09-06Science Education in the 21st Century: Using the tools of science to teach science
2016-09-06Generic Programming in the Parallel Boost Graph Library
2016-09-06Candidate talk: On the Evaluation and Extraction of Thread-Level Parallelism in Ordinary Programs
2016-09-06Developing the Best Life and Death Solver in Go
2016-09-06No Ifs, Ands, or Buts: Uncovering the Simplicity of Conditionals


Tags:
microsoft research