👷 Seminar on Machine Learning, Information Retrieval, and Scientific Visualization

[Tomáš Gregor]: Introduction to Quantum Neural Networks 14. 11. 2024

Visual Abstract

Visual abstract


Abstract

In recent years, enormous progress has been made in studying and developing artificial neural networks and machine learning models that can approximate any well-behaved function to an arbitrary precision. These models can perform even superhuman tasks, such as predicting the spatial structure of any protein just from its sequence of amino acids.

Another cutting-edge research area is quantum computing, which studies using the quantum properties of polarized light or supercooled materials for computation. Researchers hope to use the properties of these quantum computations to solve problems that would take more than the universe's lifetime to compute on a classical computer.

At the intersection of these two research areas lie quantum neural networks, a rapidly growing research topic with much promise but little concrete results thus far. In my presentation, I will lay out the theory behind the components of quantum computing: qubits, quantum circuits, and quantum algorithms. Armed with the foundations of quantum computing, the architecture of quantum neural networks, the methods used to train these models, results, problems, and advantages over classical neural networks will be discussed.

Slides

TBA

Lecture Recordings

Introduction to Quantum Neural Networks

Readings

  1. K. Beer, Quantum neural networks, in arXiv (Cornell University), 2022, pp. 21-102. doi.org/10.48550/arxiv.2205.08154 
  2. Y. Kwak, W. J. Yun, S. Jung, and J. Kim, Quantum Neural Networks: Concepts, applications, and challenges, arXiv (Cornell University), Jan. 2021, doi.org/10.48550/arxiv.2108.01468 
  3. M. Ragone et al., A Lie algebraic theory of barren plateaus for deep parameterized quantum circuits, Nature Communications, vol. 15, no. 1, Aug. 2024, doi.org/10.1038/s41467-024-49909-3 
  4. M. Schuld, R. Sweke, and J. J. Meyer, Effect of data encoding on the expressive power of variational quantum-machine-learning models, Physical Review. A/Physical Review, A, vol. 103, no. 3, Mar. 2021, doi.org/10.1103/physreva.103.032430 

Catering

Acai

Předchozí
Následující