Machine learning is one of the most sought after field as of today. With the availability and use of more sophisticated computers came more data and more power to process them. Even our regular computers nowadays are able to analyze data of considerable sizes. But when the size of data explodes, the classical machines consume a large amount of time to provide us with any useful result.
Quantum computing is an entirely new computational paradigm that exploits the quantum mechanical properties of nature to simulate and compute various problems that are considered hard in classical computers. Quantum computers have been shown to solve certain problems like integer factorization and particle simulation exponentially faster and problems like unordered search and period finding in Boolean functions quadratically faster than their classical counterparts.
So the natural question to ask is can quantum computers be used to solve data tasks faster than the classical computer? This talk aims to address this issue.
Machine learning is one of the most sought after field as of today. With the availability and use of more sophisticated computers came more data and more power to process them. Even our regular computers nowadays are able to analyze data of considerable sizes. But when the size of data explodes, the classical machines consume a large amount of time to provide us with any useful result.
Quantum computing is an entirely new computational paradigm that exploits the quantum mechanical properties of nature to simulate and compute various problems that are considered hard in classical computers. Quantum computers have been shown to solve certain problems like integer factorization and particle simulation exponentially faster and problems like unordered search and period finding in Boolean functions quadratically faster than their classical counterparts.
So the natural question to ask is can quantum computers be used to solve data tasks faster than the classical computer? This talk aims to address this issue.
A great reading material that serves as an introduction to this talk is the following paper: https://arxiv.org/pdf/1611.09347.pdf