alterlab-pennylane

What problem does it solve?

PennyLane enables researchers to build and train hybrid quantum-classical models, bridging quantum circuits with classical ML workflows to accelerate discovery.

Core Features & Use Cases

• Variational circuits: implement trainable quantum layers that interface with PyTorch/JAX/TF.
• Device-agnostic workflows: run on simulators or hardware backends (IBM, Google, IonQ, etc.).
• Education and research: ideal for academic experiments, prototyping quantum ML models, and teaching quantum ML concepts.
• Example: combine a variational quantum layer with a classical classifier to perform binary classification tasks on small datasets.

Quick Start

Create a simple hybrid model by coupling a quantum circuit to a classical network and start training on a test dataset.