The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
This work provides a novel theoretical framework for deep learning that bridges quantum computing and neural networks, potentially enabling new computational techniques and applications in quantum AI.
The authors developed a quantum field theory formalism for deep learning, representing neural networks with quantum gates and introducing 'Hintons' as fundamental excitations, enabling efficient implementation on optical quantum computers and classical simulation in a semi-classical limit.
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.