Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.12202/8960
Title: | Overview of vector similarity for machine learning |
Authors: | Feltenberger, Dave Zolty, Daniel |
Keywords: | information retrieval data mining machine learning vector similarity applications clustering |
Issue Date: | May-2023 |
Publisher: | Yeshiva University |
Citation: | Zolty, D. (2023, May). Overview of vector similarity for machine learning [Unpublished undergraduate honors thesis, Yeshiva University]. |
Series/Report no.: | Jay and Jeanie Schottenstein Honors Program;May 2023 |
Abstract: | In the realm of information retrieval, data mining, and machine learning, measuring the similarity between objects is a fundamental task. One powerful approach to quantifying similarity is through the use of vectors. Over the years, the concept of vector similarity has evolved, providing researchers and practitioners with valuable tools for various applications. One of the most commonly used applications is machine learning. When used in such applications, it enables the comparison and quantification of similarity between objects or data points represented as vectors. It offers valuable insights and capabilities for tasks such as clustering, classification, recommendation systems, and information retrieval. However, while vector similarity is a powerful tool, it also has limitations that need to be considered. This essay explores the importance and restraints of vector similarity in the context of machine learning....¶Vector similarity is a fundamental concept in machine learning, providing a framework to quantify similarity and enable diverse applications. From feature comparison and clustering to recommendation systems and information retrieval, vector similarity empowers machine learning algorithms to discover patterns, make informed decisions, and improve user experiences. However, challenges such as high-dimensional data, noise, and interpretability need to be carefully addressed. By understanding the importance and limitations of vector similarity, researchers and practitioners can harness its power effectively and (missing text from Conclusion?). |
Description: | Undergraduate honors thesis / Opt Out |
URI: | https://hdl.handle.net/20.500.12202/8960 |
Appears in Collections: | Jay and Jeanie Schottenstein Honors Student Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Daniel Zolty Honors Thesis OptOut opt.pdf Restricted Access | 206.71 kB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License