QCML User Guide

Welcome to QCML (Quantum Cognition Machine Learning), a powerful library for machine learning developed by Qognitive, Inc. The aim of this guide is to help a user get started with QCML and explore its features.

Installation

QCML is available in two editions:

Community Edition

pip install hone-io

The community edition has the following restrictions:

Parameter	Limit	Description
Input Features	100	Maximum number of input features/operators
Output Features	12	Maximum number of output features/operators
Hilbert Space Dimension	8	Maximum dimension of the quantum state space
Training Samples	1,000	Maximum number of training samples per batch

Enterprise Edition

The enterprise edition has no restrictions and is suitable for larger datasets and more complex models. To install:

pip install hone-io-enterprise

For the enterprise edition, you need a valid license that can be requested at https://www.qognitive.io/api-request/.

Quick Start

Both editions of QCML provide scikit-learn API wrappers for easy integration into existing workflows:

from honeio.integrations.sklearn.qcmlsklearn import QCMLRegressor
from sklearn.metrics import r2_score

# Create and train a QCML regressor
model = QCMLRegressor(hilbert_space_dim=8, epochs=1000, lr=0.1)
model.fit(X_train, y_train)

# Make predictions and evaluate performance
y_pred = model.predict(X_test)
print("R^2 score:", r2_score(y_test, y_pred))

from honeio.integrations.sklearn.qcmlsklearn import QCMLClassifier
from sklearn.metrics import roc_auc_score

# Create and train a QCML classifier
model = QCMLClassifier(hilbert_space_dim=8, epochs=1000, lr=0.1)
model.fit(X_train, y_train)

# Make predictions and evaluate performance
y_score = model.predict_proba(X_test)
print("ROC AUC score:", roc_auc_score(y_test, y_score))

Detailed documentation for the scikit-learn API can be found in the API Reference.

Full examples can be found in the Examples section.

License

This software is licensed under a proprietary license. See the LICENSE file for details.