Jun 12–16, 2023
Perimeter Institute for Theoretical Physics
America/Toronto timezone

Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition

Jun 16, 2023, 11:15 a.m.
45m
PI/1-100 - Theatre (Perimeter Institute for Theoretical Physics)

PI/1-100 - Theatre

Perimeter Institute for Theoretical Physics

190

Speaker

Estelle Inack (Perimeter Institute)

Description

Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices. However, their training, architectural design, and hyperparameter tuning remain challenging as these involve multiple computationally expensive combinatorial optimization problems. Here we introduce quantum hypernetworks as a mechanism to train binary neural networks on quantum computers, which unify the search over parameters, hyperparameters, and architectures in a single optimization loop. Through classical simulations, we demonstrate that of our approach effectively finds optimal parameters, hyperparameters and architectural choices with high probability on classification problems including a two-dimensional Gaussian dataset and a scaled-down version of the MNIST handwritten digits. We represent our quantum hypernetworks as variational quantum circuits, and find that an optimal circuit depth maximizes the probability of finding performant binary neural networks. Our unified approach provides an immense scope for other applications in the field of machine learning.

Presentation materials

There are no materials yet.

External references