2 Low - Dimensional Search and K - D Trees
نویسنده
چکیده
In the similarity search problem, we are given a database D consisting of n items. Given a query q, the goal is to report all x ∈ D that are “near” the query point q. Such a problem is of fundamental importance to recommendation systems: Given an image, what images are similar; given a movie and a measure of similarity between movies, what are other movies to recommend to the user; given a product purchased, what are similar products to recommend; and so on. In typical settings, n is massive, say all movies on Netflix, or all products on Amazon. Solving the near-neighbor problem requires two intertwined ingredients:
منابع مشابه
P´olya Urn Models and Connections to Random Trees: A Review
This paper reviews P´olya urn models and their connection to random trees. Basic results are presented, together with proofs that underly the historical evolution of the accompanying thought process. Extensions and generalizations are given according to chronology: • P´olya-Eggenberger’s urn • Bernard Friedman’s urn • Generalized P´olya urns • Extended urn schemes • Invertible urn schemes ...
متن کاملThe Design of Custom Vlsi for Learning by Example
Learning by example is a technique used widely in pattern classiication and function approximation tasks. Neural networks and memory based approaches are common implementations of learning by example, and both have speed bottlenecks. Neural netowrks require several iterations to tune parameters based on an example database, and memory based approaches require repeated queries of close matches f...
متن کاملOn two-dimensional Cayley graphs
A subset W of the vertices of a graph G is a resolving set for G when for each pair of distinct vertices u,v in V (G) there exists w in W such that d(u,w)≠d(v,w). The cardinality of a minimum resolving set for G is the metric dimension of G. This concept has applications in many diverse areas including network discovery, robot navigation, image processing, combinatorial search and optimization....
متن کاملOptimizing Search Strategies in k-d Trees
While k-d trees have been widely studied and used, their theoretical advantages are often not realized due to ineffective search strategies and generally poor performance in high dimensional spaces. In this paper we outline an effective search algorithm for k-d trees that combines an optimal depth-first branch and bound (DFBB) strategy with a unique method for path ordering and pruning. Our ini...
متن کاملWhich Spatial Partition Trees are Adaptive to Intrinsic Dimension?
Recent theory work has found that a special type of spatial partition tree – called a random projection tree – is adaptive to the intrinsic dimension of the data from which it is built. Here we examine this same question, with a combination of theory and experiments, for a broader class of trees that includes k-d trees, dyadic trees, and PCA trees. Our motivation is to get a feel for (i) the ki...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017