We propose a neural-network-based model capable of learning the broad landscape of working regimes in quantum dot simulators and using this knowledge to autotune these devices—based on transport measurements—toward obtaining Majorana modes in the structure. The model is trained in an unsupervised manner on synthetic data in the form of conductance maps, using a physics-informed loss that incorporates key properties of Majorana zero modes. We show that, with appropriate training, a deep vision-transformer network can efficiently memorize the relations between Hamiltonian parameters and structures on conductance maps and use them to propose parameter updates for a quantum dot chain that drives the system toward a topological phase. Starting from a broad range of initial detunings in parameter space, a single update step is sufficient to generate nontrivial zero modes. Moreover, by enabling an iterative tuning procedure—where the system acquires updated conductance maps at each step—we demonstrate that the method can address a much larger region of the parameter space.

Close

PrevNext

View figure in article

• Majorana bound states
• Quantum information with solid state qubits
• Artificial neural networks
• Quantum dot qubits
• Topological qubits
• Machine learning
• Radio frequency techniques
• Unsupervised learning