Video URL

https://pirsa.org/16080001

Comparing Classical and Quantum Methods for Supervised Machine Learning

Kapoor, A. (2016). Comparing Classical and Quantum Methods for Supervised Machine Learning. Perimeter Institute for Theoretical Physics. https://pirsa.org/16080001

Kapoor, Ashish. Comparing Classical and Quantum Methods for Supervised Machine Learning. Perimeter Institute for Theoretical Physics, Aug. 08, 2016, https://pirsa.org/16080001 

          @misc{ scivideos_PIRSA:16080001,
            doi = {10.48660/16080001},
            url = {https://pirsa.org/16080001},
            author = {Kapoor, Ashish},
            keywords = {Quantum Matter},
            language = {en},
            title = {Comparing Classical and Quantum Methods for Supervised Machine Learning},
            publisher = {Perimeter Institute for Theoretical Physics},
            year = {2016},
            month = {aug},
            note = {PIRSA:16080001 see, \url{https://scivideos.org/pirsa/16080001}}
          }

Ashish Kapoor Microsoft Corporation

DOI 10.48660/16080001
Source Repository PIRSA
Collection
Talk Type Conference
Subject

Abstract

Supervised Machine Learning is one of the key problems that arises in modern big data tasks. In this talk, I will first describe several different classical algorithmic paradigms for classification and then contrast them with quantum algorithmic constructs. In particular, we will look at classical methods such as the nearest neighbor rule, optimization based algorithms (e.g. SVMs), Bayesian inference based techniques (e.g. Bayes point machine) and provide a unifying framework so that we can get a deeper understanding about the quantum versions of the methods.