LLY-NN for Neural Network is an exciting project of the LILY Project that models simple neural networks on quantum computers. In this approach, the potentials that are usually transferred from neuron to neuron are replaced by phase shifts, mediated through quantum entanglement and bias. This method leverages the advantages of quantum mechanics to optimize and enhance the performance of neural networks.
LLY-NN is available on the LILY QML platform, making it accessible for researchers and developers.
For inquiries or further information, please contact: [email protected].
| Role | Name | Links |
|---|---|---|
| Project Lead | Leon Kaiser | ORCID, GitHub |
| Supporting Contributors | Eileen Kühn | GitHub, KIT Profile |
| Supporting Contributors | Max Kühn | GitHub |
Classical neural networks have input neurons that transmit their values to subsequent neurons. In our approach with LLY-NN, the first two L-Gates are responsible for defining the input values of the two neurons. These values are then entangled onto a third qubit. An additional L-Gate sets the bias for processing the entangled states. This approach effectively leverages quantum mechanics to optimize the transmission of information within the network.
