An approach for automated generation of quantum computing models using deep learning

Quantum computing promises remarkable computational power with minimal energy consumption. However, the complexity of developing quantum circuits and codes hinders fully exploiting this potential. The study proposes an approach based on the automatic quantum circuit and code generation based on deep learning. It enables the resynthesis of existing circuits and the creation of new ones from undefined inputs. The system transforms inputs into reversible truth tables, generates a quantum unitary matrix, corrects errors, optimizes it, and converts it into a quantum code or circuit. This approach has been implemented on circuits and codes that involve up to five variables. Rigorous evaluations include both the Deep Neural Network and the overall approach. Although the DNN output does not guarantee absolute correctness, our approach compensates with supplementary processes, ensuring the precise generation of quantum codes and circuits. Comprehensive testing confirmed the approach's effectiveness in overcoming challenges in quantum circuit and code development.