Quantum Machine Learning

Solve machine learning problems with the unique neutral-atom computer from QuEra

Quantum machine learning is widely considered a promising application for near-term quantum computers, with potential in computer vision, natural language processing, and finding general patterns in large data sets.

Aquila's 256 qubits allow encoding a very large parameter space, and our system-wide coherence and fast entanglement propagation deliver dramatic performance increases over other quantum approaches.

Our recent paper describing quantum machine learning results with 108 qubits, the largest QML experiment to date is here, and a Webinar recording describing the approach and results is here.

A recent Webinar showcased results obtained by Deloitte Consulting when using QuEra's quantum machine learning workflow. Watch the recording here.

Benefits

Obtain solutions to complex machine learning problems that cannot currently be solved with gate-based quantum computers.

Enjoy an increased robustness to noise.

Leverage quantum dynamics to implement powerful algorithms such as reservoir machine learning.

Effective for classification as well as prediction tasks.

Example results for QML recognition of digits

Get Started

Learn more about machine learning with neutral atoms

Read this paper describing the largest QML experiment to date.

arrow

Our expert team is happy to discuss how we might be able to help

arrow

Additional information and code samples

Watch a recent Webinar explaining quantum reservoir computing and recent results.

arrow

Watch a recent QML Webinar with Deloitte Consulting

arrow

Github code samples and tutorials

arrow