Quantum error mitigation with neural networks

July issue now live

Bennewitz, E.R., Hopfmueller, F., Kulchytskyy, B. et al. Neural Error Mitigation of Near-Term Quantum Simulations.

  • Elizabeth R. Bennewitz
  • Florian Hopfmueller
  • Pooya Ronagh
Article

Nature Machine Intelligence is a Transformative Journal; authors can publish using the traditional publishing route OR via immediate gold Open Access.

Our Open Access option complies with funder and institutional requirements.

Advertisement

  • Finding stable radical compounds for redox flow batteries is a challenging molecular design task. Sowndarya et al. combine an AlphaZero-based framework with a surrogate objective function trained on quantum chemistry simulations to generate suitable radical candidates that are stable. The approach promises to contribute to the development of low-cost, reliable energy storage technologies.

    • Shree Sowndarya S. V.
    • Jeffrey N. Law
    • Peter C. St. John
    Article Open Access
  • Targeted drug delivery is an exciting application of nanorobotics, but directing particles in the blood stream to the right location and in sufficient number is challenging. Gu and colleagues have developed a microtubule scaffold with embedded micromagnets that allows cargo, such as drug particles, to be transported in microvascular networks with precision and speed.

    • Hongri Gu
    • Emre Hanedan
    • Bradley J. Nelson
    Article
  • So-called noisy intermediate-scale quantum devices will be capable of a range of quantum simulation tasks, provided that the effects of noise can be sufficiently reduced. A neural error mitigation approach is developed that uses neural networks to improve the estimates of ground states and ground-state observables of molecules and quantum systems obtained using quantum simulations on near-term devices.

    • Elizabeth R. Bennewitz
    • Florian Hopfmueller
    • Pooya Ronagh
    Article
  • Using the natural dynamics of a legged robot for locomotion is challenging and can be computationally complex. A newly designed quadruped robot called Morti uses a central pattern generator inside two feedback loops as an adaptive method so that it efficiently uses the passive elasticity of its legs and can learn to walk within 1 h.

    • Felix Ruppert
    • Alexander Badri-Spröwitz
    Article Open Access
  • Artificial DNA circuits that can perform neural network-like computations have been developed, but scaling up these circuits to recognize a large number of patterns is a challenging task. Xiong, Zhu and colleagues experimentally demonstrate a convolutional neural network algorithm using a synthetic DNA-based regulatory circuit in vitro and develop a freeze–thaw approach to reduce the computation time from hours to minutes, paving the way towards more powerful biomolecular classifiers.

    • Xiewei Xiong
    • Tong Zhu
    • Hao Pei
    Article
  • An end-to-end machine learning approach that can learn which mechanisms determine cell fate and competition from a large time-lapse microscopy dataset is developed. The approach makes use of a probabilistic autoencoder to learn an interpretable representation of the organization of cells, and provides cell fate predictions that can be tested in drug screening experiments.

    • Christopher J. Soelistyo
    • Giulia Vallardi
    • Alan R. Lowe
    Article
    • Designing viable molecular candidates is pivotal to devising low-cost and sustainable storage systems. A reinforcement learning framework has been developed that can identify stable candidates for redox flow batteries in the large search space of organic radicals.

      • Yang Cao
      • Cher Tian Ser
      • Alán Aspuru-Guzik
      News & Views
    • Directed, active transport of cargo is essential for life on all length scales. A new system of artificial microtubules — consisting of a fibre with an embedded periodic array of magnetic inclusions — provides controlled active transport of microcargo by a rotating magnetic field, even under adverse flow conditions.

      • Gerhard Gompper
      News & Views
    • Deep learning models for sequential data can be trained to make accurate predictions from large biological datasets. New tools from computer vision and natural language processing can help us make these models interpretable to biologists.

      • Ahmed M. Alaa
      News & Views
    • Microscopy-based drug screens with fluorescent markers can shed light on how drugs affect biological processes. Without adding markers and imaging channels, which is cumbersome and costly, a new generative deep-learning method extracts new fluorescence channels from images, potentially improving the drug-discovery pipeline.

      • Florian Heigwer
      News & Views
    • Neural networks can be implemented by using purified DNA molecules that interact in a test tube. Convolutional neural networks to classify high-dimensional data have now been realized in vitro, in one of the most complex demonstrations of molecular programming so far.

      • William Poole
      News & Views
  • As with last summer, COVID-19 is still with us, but there is a semblance of what life was like before the pandemic. Here, we recommend AI podcasts from the past year that may inform, inspire or entertain, as we get an opportunity to travel or take time away from regular activities.

    Editorial
  • China is pushing ahead of the European Union and the United States with its new synthetic content regulations. New draft provisions would place more responsibility on platforms to preserve social stability, with potential costs for online freedoms. They show that the Chinese Communist Party is prepared to protect itself against the unique threats of emerging technologies.

    • Emmie Hine
    • Luciano Floridi
    Comment
  • Artificial intelligence (AI) can support managers by effectively delegating management decisions to AI. There are, however, many organizational and technical hurdles that need to be overcome, and we offer a first step on this journey by unpacking the core factors that may hinder or foster effective decision delegation to AI.

    • Stefan Feuerriegel
    • Yash Raj Shrestha
    • Ce Zhang
    Comment
  • Soon into the COVID-19 pandemic, civil-rights groups raised the alarm over the increase in digital surveillance infringing on individual rights. But there are other potential harms as tech companies accelerate their expansion into new areas essential to public-service provision.

    Editorial