Quantum Based Learning with Binary Neural Network

Andrew Haverly, Shahram Rahimi, M. A. Novotny

This paper presents an adaptation of the quantum binary neural network (QBNN) to reinforcement learning, enabling the network to efficiently train on a classically intractable number of agent-environment-state-action-reward combinations. We demonstrate the feasibility of this approach through its application to the gridworld task, showcasing the potential of QBNNs in handling complex, high-dimensional reinforcement learning problems. This work provides a foundation for further exploration of QBNNs in more complex reinforcement learning environments.

Om Prakash Patel, Aruna Tiwari

Quantum computing and classical machine learning have recently converged, offering new avenues for improved classification tasks.This research explores the potential of quantum-enhanced neural networks for binary classification.It delves into the quantum feature encoding process, the architecture of quantumenhanced neural networks, extensive experiments on synthetic data, and discusses implications and future directions in this emerging field.

Bu-Qing Chen, Xu-Feng Niu

Juan Carrasquilla, Mohamed Hibat-Allah, Estelle M. Inack +4 more

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 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.

Davide Pastorello