Lecture 11 : Nearest Neighbor Search and the Curse of Dimensionality
نویسنده
چکیده
Nearest neighbor search is a fundamental computational building block in computer vision, graphics, data mining, machine learning, and many other subfields. As an example, consider a simple k-nearestneighbor-classifier which, for each point predicts its class by the a majority vote over its neighbors’ classes. As simplistic as this classifier sounds, it actually performs very well in many scenarios.
منابع مشابه
Dimension Reduction
The “curse of dimensionality” refers to various phenomena that arise when analyzing and organizing data in high dimensions. For example, the solution to nearest neighbor problem grows exponentially with the dimension. Therefore dimension reduction, the process of representing data in lower dimensions while preserving the essential properties, is very useful. Common techniques include Singular V...
متن کاملCOS 424 : Interacting with Data
The previous lecture defined the Nearest Neighbor Algorithm and discussed how it suffers from the curse of dimensionality. This means that as the number of dimensions increase the Nearest Neighbor algorithm performs poorer and poorer. To better understand the curse of dimensionality with regard to the Nearest Neighbor algorithm one must understand what higher dimensions look like. The following...
متن کاملA Parallel Algorithms on Nearest Neighbor Search
The (k-)nearest neighbor searching has very high computational costs. The algorithms presented for nearest neighbor search in high dimensional spaces have have suffered from curse of dimensionality, which affects either runtime or storage requirements of the algorithms terribly. Parallelization of nearest neighbor search is a suitable solution for decreasing the workload caused by nearest neigh...
متن کاملCS168: The Modern Algorithmic Toolbox Lecture #4: Dimensionality Reduction
Lectures #1 and #2 discussed “unstructured data”, where the only information we used about two objects was whether or not they were equal. Last lecture, we started talking about “structured data”. For now, we consider structure expressed as a (dis)similarity measure between pairs of objects. There are many such measures; last lecture we mentioned Jaccard similarity (for sets), L1 and L2 distanc...
متن کاملNearest Neighbor Search using Kd-trees
We suggest a simple modification to the kd-tree search algorithm for nearest neighbor search resulting in an improved performance. The Kd-tree data structure seems to work well in finding nearest neighbors in low dimensions but its performance degrades even if the number of dimensions increases to more than three. Since the exact nearest neighbor search problem suffers from the curse of dimensi...
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 2013