First end-to-end quantum machine learning Python SDK for classification models.
Stafford Computing LLC
MAIN FEATURES
Non-quantum coding required
Customized quantum embeddings
End-to-end QML process
The structure of the SDK will allow the data to be executed in different ways for quantum encoding (Qiskit, PennyLane, and proprietary) to extract the best result possible after running the whole process, including algorithms and postprocessing.
The SDK does not require knowledge of any quantum programming language or even expertise in quantum principles or linear algebra. The process of running quantum algorithms will require just a Python environment, a few parameters, and execution.
This Python library will execute an end-to-end process with regards to classification models. Preprocessing, encoding, algorithms, and postprocessing are stages fully embedded in our system.
Fully compatible with well-known quantum SDKs :
Let's discover together the path towards quantum technologies adoption inside your company
Do you prefer direct advice in the quantum field?
Address: 8 The Green, Suite 12267, Dover, DE 19901, USA.
Contact us: info@staffordcomputing.com
QUANTUM software development kit
End-to-end quantum machine learning classification model execution
Stafford Computing developed the Falcondale Python SDK with the clear objective of providing a fast and easy path for data scientists, data engineers, analysts, developers, and any quantum enthusiast (with a little Python knowledge) to execute hybrid quantum-classical and quantum-inspired algorithms. This SDK will allow the users to input their classical data (in the same way that is used for classical machine learning models), set up the parameters for the quantum part execution, and later receive the results of the classification model.
The SDK will not require knowledge about quantum programming or physics, but we recommend exploring more deeply some processes in the quantum part to be aware of the potential benefits that this technology can bring to the client's business.
Our tech stack ecosystem
Features and details:
custom quantum embeddings
Classical Data Space
Classical data usually represents a challenging process if the objective is to classify the datapoints using linear approaches (e.g., SVM). Finding the most accurate way to separate both (or more) classes can be a very difficult process to execute when high accuracy is required.
Quantum Hilbert Space
By the use of quantum embeddings for quantum machine learning algorithms, the data can be represented in a larger dimensional space (Hilbert Space). This technique can be useful in specific cases to extract better separability from non-linearly separable datapoints. Falcondale Python SDK includes customized quantum embedding operations to boost the classification results.
Explore the potential benefits of quantum machine learning in your own projects and classification challenges.
Ready to test yourself?