The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
arXiv:2103.04913
Abstract
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 formulation is well suited for optical quantum computing, and provides quantum deformations of neural networks that can be run efficiently on those devices. Finally, we discuss a semi-classical limit of the quantum deformed models which is amenable to classical simulation.
References in corpus (16)
- Quantum algorithm for solving linear systems of equations
- Deep Learning with Coherent Nanophotonic Circuits
- Quantum Convolutional Neural Networks
- Quantum computation over continuous variables
- Continuous variable quantum information: Gaussian states and beyond
- Efficient Learning for Deep Quantum Neural Networks
- Efficient Classical Simulation of Continuous Variable Quantum Information Processes
- Reconstruction of Gaussian quantum mechanics from Liouville mechanics with an epistemic restriction
- Quantum machine learning over infinite dimensions
- Invariant and Equivariant Graph Networks
- Dissecting Neural ODEs
- A Universal Training Algorithm for Quantum Deep Learning
- Augmented Neural ODEs
- A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
- Learning Symmetries of Classical Integrable Systems
- Probabilistic Numeric Convolutional Neural Networks