Artificial intelligence and machine learning for quantum technologies (2024)

Authorization Required

×

×

• 

  Figure 1

  Overview of tasks in the area of quantum technologies that machine learning and artificial intelligence can help solve better, as explained in this perspective article.

  Reuse & Permissions

• 

  Figure 2

  Basics of neural networks and machine learning techniques. (a)Operation of a single artificial neuron. (b)Structure of a neural network with dense layers. (c)Evolution of the network's parameters $\theta$ (which contains weights and biases of the neural network) in the cost function landscape using stochastic gradient descent. For every step (orange arrows) the gradients of the averaged cost function with respect to $\theta$ (gray dashed line) are approximated by the gradient averaged over a random batch. The parameters $\widehat{\theta }$ minimize the averaged cost function. (d)Classification of unlabeled data. (e) Reinforcement learning problem modeled as Markov decision process.

  Reuse & Permissions

• 

  Figure 3

  State estimation via neural networks. (a)Measurements on many identical copies of a quantum state can be processed to produce an estimate of the quantum state. (b)A continuous weak measurement on a single quantum system can be used to update the estimated state. In both (a)and (b), a single network is trained to estimate arbitrary states correctly. (c)One can also train a network-based generative model to reproduce the statistics of a quantum state, i.e., to sample from the probability distribution. Training requires many identical copies that can be measured, so the statistics can be learned. Here one network represents only a single quantum state. It can be extended to handle measurements in arbitrary bases.

  Reuse & Permissions

• 

  Figure 4

  Machine learning for parameter estimation in quantum devices. (a)A typical scenario, with the measurement result statistics depending on both some tuneable measurement setting and the unknown parameter(s), here represented as phase shifts in a Mach-Zehnder setup. (b)An adaptive measurement strategy can be illustrated as a tree, with branches on each level corresponding to different measurement outcomes. Depending on those outcomes, a certain next measurement setting (indicated as “${\alpha }_j$”) needs to be selected. Finding the best strategy is a challenging task, as it corresponds to searching the space of all such trees. (c)Neural generative models can be used to randomly sample possible future measurement outcomes (here 2D current-voltage maps as in[68]) that are compatible with previous measurement outcomes. This is helpful for selecting the optimal next measurement location. Different random locations in latent space result in different samples. (d)Measurement outcome vs measurement setting for five possible underlying parameter values (different curves; measurement uncertainty indicated via thickness). We aim to maximize the information gain, i.e., choose the setting which best pinpoints the parameter (which is not equivalent to maximizing the uncertainty of the outcome).

  Reuse & Permissions

• 

  Figure 5

  (a)The eventual goal of model-free reinforcement learning is the direct application to experiments, which then can be treated as a black box. Many actual implementations, however, use model-free RL techniques applied to model-based simulations. (b)Model-based reinforcement learning directly exploits the availability of a model, e.g., taking gradients through differentiable dynamics.

  Reuse & Permissions

• 

  Figure 6

  Discovery of quantum experiments. Quantum optics experiments can be represented by colored graphs. Using the most general, complete graph as a starting representation, the AI's goal is to extract the conceptual core of the solution, which can then be understood by human scientists. The solution can then be translated to numerous different experimental configurations[113].

  Reuse & Permissions

• 

  Figure 7

  Discovery of quantum circuits and feedback strategies with discrete gates. (a)A reinforcement-learning agent acts on a multiqubit system by selecting gates, potentially conditioned on measurement outcomes, finding an optimized quantum circuit or quantum feedback strategy. (b)A fixed layout quantum circuit with adjustable parameters that can be optimized via gradient ascent to achieve some goal like state preparation or variational ground state search (possibly including feedback).

  Reuse & Permissions

• 

  Figure 8

  Quantum error correction. Syndrome interpretation in a surface code as a task that a neural network can be trained to perform.

  Reuse & Permissions

×