• Corpus ID: 232147869

The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning

@inproceedings{Bondesan2021TheHI,
  title={The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning},
  author={Roberto Bondesan and Max Welling},
  booktitle={International Conference on Machine Learning},
  year={2021}
}
In this work we develop a quantum field theory formalism for deep learning, where input signals are encoded in Gaussian states, a generalization of Gaussian processes which encode the agent’s uncertainty about the input signal. We show how to represent linear and non-linear layers as unitary quantum gates, and interpret the fundamental excitations of the quantum model as particles, dubbed “Hintons”. On top of opening a new perspective and techniques for studying neural networks, the quantum… 

Figures from this paper

A Leap among Quantum Computing and Quantum Neural Networks: A Survey

First, basic concepts related to quantum computations are introduced, and then the core functionalities of technologies that implement the Gate Model and Adiabatic Quantum Computing paradigms are explained.

Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws & Recurrence

Recent advances in quantum computing and in particular, the introduction of quantum GANs, have led to increased interest in quantum zero-sum game theory, extending the scope of learning algorithms

The edge of chaos: quantum field theory and deep neural networks

This work explicitly construct the quantum field theory corresponding to a general class of deep neural networks encompassing both recurrent and feedforward architectures, and provides a first-principles approach to the rapidly emerging NN-QFT correspondence.

Towards quantifying information flows: relative entropy in deep neural networks and the renormalization group

The analogy between the renormalization group (RG) and deep neural networks, wherein subsequent layers of neurons are analogous to successive steps along the RG, is investigated, and the monotonic increase confirms the connection between the relative entropy and the c-theorem.

References

SHOWING 1-10 OF 49 REFERENCES

Quantum Deformed Neural Networks

We develop a new quantum neural network layer designed to run efficiently on a quantum computer but that can be simulated on a classical computer when restricted in the way it entangles input states.

Continuous-variable quantum neural networks

A general method for building neural networks on quantum computers and how a classical network can be embedded into the quantum formalism and propose quantum versions of various specialized model such as convolutional, recurrent, and residual networks are introduced.

A Universal Training Algorithm for Quantum Deep Learning

We introduce the Backwards Quantum Propagation of Phase errors (Baqprop) principle, a central theme upon which we construct multiple universal optimization heuristics for training both parametrized

Efficient Learning for Deep Quantum Neural Networks

This work proposes the use of quantum neurons as a building block for quantum feed-forward neural networks capable of universal quantum computation and describes the efficient training of these networks using the fidelity as a cost function and provides both classical and efficient quantum implementations.

Quantum Machine Learning over Infinite Dimensions.

This work presents the critical subroutines of quantum machine learning algorithms for an all-photonic continuous-variable quantum computer that can lead to exponential speedups in situations where classical algorithms scale polynomially.

Towards quantum machine learning with tensor networks

A unified framework is proposed in which classical and quantum computing can benefit from the same theoretical and algorithmic developments, and the same model can be trained classically then transferred to the quantum setting for additional optimization.

Quantum convolutional neural networks

A quantum circuit-based algorithm inspired by convolutional neural networks is shown to successfully perform quantum phase recognition and devise quantum error correcting codes when applied to arbitrary input quantum states.

Classification with Quantum Neural Networks on Near Term Processors

This work introduces a quantum neural network, QNN, that can represent labeled data, classical or quantum, and be trained by supervised learning, and shows through classical simulation that parameters can be found that allow the QNN to learn to correctly distinguish the two data sets.

Gaussian quantum information

This review focuses on continuous-variable quantum information processes that rely on any combination of Gaussian states, Gaussian operations, and Gaussian measurements, including quantum communication, quantum cryptography, quantum computation, quantum teleportation, and quantum state and channel discrimination.

Gaussian-Wigner distributions in quantum mechanics and optics.

The Wigner distribution method is shown to be a convenient framework for characterizing Gaussian kernels and their unitary evolution under Sp(2n,openR) action and the nontrivial role played by a phase term in the kernel is brought out.