PIRSA:16060005 Scientific Series Condensed Matter

DOI10.48660/16060005

Series: Quantum Matter

(2016). Machine Learning with Quantum-Inspired Tensor Networks. Perimeter Institute. https://pirsa.org/16060005

Machine Learning with Quantum-Inspired Tensor Networks. Perimeter Institute, Jun. 14, 2016, https://pirsa.org/16060005 

@misc{ pirsa_PIRSA:16060005,
  doi = {10.48660/16060005},
  url = {https://pirsa.org/16060005},
  author = {},
  keywords = {Condensed Matter},
  language = {en},
  title = {Machine Learning with Quantum-Inspired Tensor Networks},
  publisher = {Perimeter Institute},
  year = {2016},
  month = {jun},
  note = {PIRSA:16060005 see, \url{https://pirsa.org}}
}

Abstract

Tensor networks have been very successful for approximating quantum states that would otherwise require exponentially many parameters.

I will discuss how a similar compression can be achieved in models used to machine learn data, such as sets of images, by representing the fitting parameters as a tensor network. The resulting model achieves state-of-the-art performance on standard classification tasks. I will discuss implications for machine learning research, exploring which insights from physics could be imported into this field.

Resources

Next talk

Related Talks