Showing 1–50 of 227 results

  1. Research Highlights |

  2. Research Highlights |

  3. Research Highlights |

  4. Research Highlights |

  5. Research | | Open

  6. Research | | Open

    • Accurate prediction of non-small cell... ...square error (in the supervised learning model, s- DeepBTS)... ...likelihood (in the semi-unsupervised learning model, su-DeepBTS) as... ...C-index = 0.7048 and AUC = 0.7390;... ...C-index = 0.7126 and AUC = 0.7420).... ...as a selector and could distinguish...
  7. Research | | Open

    • Machine learning has been extensively applied in... ...wide range of molecular properties and processes including mass spectrometry fragmentation... ...this dataset, we deployed a deep learning model for retention time prediction... ...to apply machine learning or first principles...
  8. Research Highlights |

  9. Reviews |

    • ...data, which vary in volume and speed of data processing,... ..., cosmic rays, gravitational waves and neutrinos. In this Expert... ...observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations... ...design of scalable...
  10. Reviews |

    • ...science, genomics largely utilizes machine learning to capture dependencies in data... and derive novel biological hypotheses.... ...data requires more expressive machine learning models. By effectively leveraging... large data sets, deep learning has transformed fields such as... ...and...
  11. Research | | Open

    • ...facing manufacturers, regulatory agencies, and health care providers. Electronic... ...evidence for assessing device safety and tracking device-related patient outcomes... ...is fractured across clinical notes and structured records. Modern machine learning methods for machine reading promise...and
  12. Research Highlights |

  13. Research | | Open

    • ...brain areas to identify diverse and subtly-differentiated morphologies. Standard... ..., however, are coarse-grained and lack precise neuroanatomic localization.... ...report a proof-of-concept deep learning pipeline that identifies specific neuropathologies... ...and cerebral amyloid angiopathy...
  14. Research | | Open

    • ...tomography (APT) facilitates nano- and atomic-scale characterization and analysis of microstructural features.... ...the interface between, for precipitate and matrix phases, in APT... ...These approaches are subjective, not scalable, and may lead to inconsistencies due... ...on deep neural...
  15. Reviews |

  16. Research | | Open

    • ...analyze how accurately supervised machine learning techniques can predict the lowest... ...to an optical speckle field. Deep neural networks with different numbers... of hidden layers and neurons per layer are trained... ...possible success of supervised machine learning tasks, namely the depth and
  17. Reviews | | Open

    • ...to explore a model of learning that proposes that various learning strategies are powerful at certain... stages in the learning cycle. The model describes... three inputs and outcomes (skill, will and thrill), success criteria,... three phases of learning (surface, deep and transfer) and an...and
  18. Research |

    • ...of diagnostic tests for anaemia and the costs associated with screening... ...can be detected via machine-learning algorithms trained using retinal fundus... ...or ethnicity, age, sex and blood pressure) or the... ...of both data types (images and study participant metadata). In... ...-only and...and
  19. Reviews |

    • Drug discovery and development pipelines are long,... complex and depend on numerous factors.... Machine learning (ML) approaches provide a... ...tools that can improve discovery and decision making for well-specified... ..., identification of prognostic biomarkers and analysis of digital pathology...
  20. Research |

    • ...holds the promise of sustainable and clean energy1. The avoidance... ...disruptions can halt power production and damage key components. Disruptions... ...present a method based on deep learning for forecasting disruptions. Our... ...as first-principles-based5 and classical machine-learning7–11...
  21. News and Views |

    • ...RNA-sequencing data uses Bayesian deep learning to correct technical artifacts and enable accurate and multifaceted downstream analyses.
  22. Reviews |

    • ...in digitized data acquisition, machine learning and computing infrastructure, AI applications... ...recent breakthroughs in AI technologies and their biomedical applications, identify... ...progress in medical AI systems, and summarize the economic, legal and social implications of AI in...
  23. Research Highlights |

  24. Reviews |

    • ...at various levels of phenotyping and from different types of resources... ...in both data-generation infrastructure and data-analysis methodologies, there... ...of debate. Addressing the potential and challenges of big data in... ...data, describe the considerations and tradeoffs taken when such...
  25. Research |

    • ...decision support systems for pathology and their deployment in clinical practice... ...we present a multiple instance learning-based deep learning system that uses only the... ...for training, thereby avoiding expensive and time-consuming pixel-wise manual... ...cell carcinoma and breast...
  26. Research |

    • ...for human genetics, precision medicine and evolutionary biology include deciphering the... ...regulatory code of gene expression and understanding the transcriptional effects of... ...mutation space. We developed a deep learning–based framework, ExPecto, that... ...wide association studies and...and
  27. Research |

    • ...they suffer from technical noise and bias that must be modeled... ...), a ready-to-use scalable framework for the probabilistic representation... and analysis of gene expression in... ...). scVI uses stochastic optimization and deep neural networks to aggregate information... ...similar cells and...
  28. Research |

    • Pattern recognition and classification of images are key... ...HPA. Second, we used deep learning to build an automated Localization... ...into 29 subcellular localization patterns and can deal efficiently with multi... ...Combining the annotations of gamers and deep learning, we applied transfer
    • ...social interactions, emotion regulation, and motivation. The high degree... of learning-dependent plasticity in these networks... ...training programs that drive meaningful and enduring improvements in impaired neural... ...training approaches for mental and addictive disorders must take...learning
  29. Research |

    • ...newly generated drug-screen dataset and demonstrate that PhEMD uncovers axes... ...to-patient variation. PhEMD is scalable, compatible with leading batch-... effect correction techniques and generalizable to multiple experimental designs...
  30. Research | | Open

    • Learning from data has led to... ...disciplines, including web, text and image search, speech recognition,... ...well as bioinformatics. Can machine learning enable similar breakthroughs in understanding... ...Here we develop an efficient deep learning approach that enables spatially and chemically...
  31. Research |

  32. Reviews |

    • ...ion migration, the switching dynamics and electrical behaviour of memristive devices... resemble those of synapses and neurons, making these devices... ...dynamical interactions between artificial synapses and neurons equip the networks with... both supervised and unsupervised learning... ...and...
  33. Research | | Open

    • Despite their interest and threat status, the number... ...through high-resolution images. Since deep convolutional neural networks (CNNs)... ...here we propose a robust and generalizable CNN-based system for... automatically detecting and counting whales in satellite and aerial images based on...
  34. Research |

    • Rapid diagnosis and treatment of acute neurological illnesses... ...such as stroke, hemorrhage, and hydrocephalus are critical to achieving... positive outcomes and preserving neurologic function—‘time... ...thus decreasing time to treatment and improving outcomes. Substantial clinical... ...and...
  35. Research | | Open

    • ...scientists to publishers, funding agencies and policy makers. We propose... a scalable, automatable framework to evaluate... ...indicators, open source tools, and participation guidelines, which come... ...resources against individual Maturity Indicators; and (3) the Evaluator,... ..., and...
  36. Research | | Open

    • ...their use in supervised machine learning. We develop a weakly... supervised deep learning model for classification of aortic... ...event. This work formalizes a deep learning baseline for aortic valve classification... and outlines a general strategy for... ...train machine learning models using...
  37. Research |

    • ...function. Here, we apply deep learning to unlabeled amino-acid sequences... ...representation that is semantically rich and structurally, evolutionarily and biophysically grounded. We show... ...(UniRep) are broadly applicable and generalize to unseen regions of... ...of natural and de novo...
  38. Research | | Open

    • ...should be sensitive to small and weak events with a variety... ...shapes, robust to background noise and non-earthquake signals, and efficient for processing large data... ...), a detector based on deep neural networks. CRED uses... ...of convolutional layers and bi-directional long-short...
  39. Research | | Open

    • Recent improvements in hardware and data collection have lowered the... ...neural systems are quite complex and difficult to design. To... ...-free method from the reinforcement learning literature, Deep Deterministic Policy Gradients (DDPG)... ...-free reinforcement learning presents an attractive...
  40. Research | | Open

    • ...increase contrast between the animal and the background in order to... ..., under dynamic environmental conditions, and in animals that are genetically... and behaviorally heterogeneous. To address... ...architectures across visually diverse mice and different environmental conditions. We...
  41. Research | | Open

    • ...fundamental issue in various scientific and engineering fields. Network theory... ...revealing the relationship between elements and their propagation; however, for... ...the network properties often transiently and complexly change. A fundamental... ...global behaviours and discovered that...
  42. Research | | Open

    • ...our understanding of substance use and addiction. In this study,... we developed a deep-learning method to automatically classify individuals... ...risk for alcohol, tobacco, and drug use based on the... ...users participated in the study. Deep convolutional neural networks for images... ...and...
  43. Research | | Open

    • ...fundamental aspects like helping patients and care teams interact and communicate in efficient and meaningful ways, which could... ...aim improvements. After heart disease and cancer, preventable medical errors... ...knowledge about their current medications and drug allergies, an often... ...and...