热点文献带您关注AI领域的最新进展——图书馆前沿文献专题推荐服务（79）

2023-05-26

在上一期热点文献推荐中，我们为您推荐了通信领域的最新发展前沿，包括基于拓扑约束的光纤信息通路扩展，用于分米级地面定位的光-无线混合网络，用于无线回程的千兆亚太赫兹通信，6G面临的十二大科学挑战。
本期我们为您选取了4篇文献，介绍人工智能领域的最新发展前沿，包括使用AlphaCode生成竞争级别的代码，可穿戴式心脏超声成像仪，用于自动驾驶汽车安全验证的密集强化学习，用于深度学习建模的肌电数字孪生，推送给相关领域的科研人员。

Competition-level code generation with AlphaCode
Li, Yujia, etc.
Science, 2022, 378(6624): 1092–1097

Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist programmers or even generate programs themselves could make programming more productive and accessible. Recent transformer-based neural network models show impressive code generation abilities yet still perform poorly on more complex tasks requiring problem-solving skills, such as competitive programming problems. Here, we introduce AlphaCode, a system for code generation that achieved an average ranking in the top 54.3% in simulated evaluations on recent programming competitions on the Codeforces platform. AlphaCode solves problems by generating millions of diverse programs using specially trained transformer-based networks and then filtering and clustering those programs to a maximum of just 10 submissions. This result marks the first time an artificial intelligence system has performed competitively in programming competitions.
阅读原文：https://www.science.org/doi/10.1126/science.abq1158

Overview of AlphaCode

A wearable cardiac ultrasound imager
Hu, Hongjie, etc.
NATURE, 2023, 613(7945): 667–675
Continuous imaging of cardiac functions is highly desirable for the assessment of long-term cardiovascular health, detection of acute cardiac dysfunction and clinical management of critically ill or surgical patients. However, conventional non-invasive approaches to image the cardiac function cannot provide continuous measurements owing to device bulkiness, and existing wearable cardiac devices can only capture signals on the skin. Here we report a wearable ultrasonic device for continuous, real-time and direct cardiac function assessment. We introduce innovations in device design and material fabrication that improve the mechanical coupling between the device and human skin, allowing the left ventricle to be examined from different views during motion. We also develop a deep learning model that automatically extracts the left ventricular volume from the continuous image recording, yielding waveforms of key cardiac performance indices such as stroke volume, cardiac output and ejection fraction. This technology enables dynamic wearable monitoring of cardiac performance with substantially improved accuracy in various environments.
阅读原文：https://www.nature.com/articles/s41586-022-05498-z

Schematics showing the exploded view of the wearable imager

Dense reinforcement learning for safety validation of autonomous vehicles
Feng, Shuo, etc.
NATURE, 2023, 615: 620–627
One critical bottleneck that impedes the development and deployment of autonomous vehicles is the prohibitively high economic and time costs required to validate their safety in a naturalistic driving environment, owing to the rarity of safety-critical events1. Here we report the development of an intelligent testing environment, where artificial-intelligence-based background agents are trained to validate the safety performances of autonomous vehicles in an accelerated mode, without loss of unbiasedness. From naturalistic driving data, the background agents learn what adversarial manoeuvre to execute through a dense deep-reinforcement-learning (D2RL) approach, in which Markov decision processes are edited by removing non-safety-critical states and reconnecting critical ones so that the information in the training data is densified. D2RL enables neural networks to learn from densified information with safety-critical events and achieves tasks that are intractable for traditional deep-reinforcement-learning approaches. We demonstrate the effectiveness of our approach by testing a highly automated vehicle in both highway and urban test tracks with an augmented-reality environment, combining simulated background vehicles with physical road infrastructure and a real autonomous test vehicle. Our results show that the D2RL-trained agents can accelerate the evaluation process by multiple orders of magnitude (103 to 105 times faster). In addition, D2RL will enable accelerated testing and training with other safety-critical autonomous systems.
阅读原文：https://www.nature.com/articles/s41586-023-05732-2

Validating safety-critical AI with the dense-learning approach

A myoelectric digital twin for fast and realistic modelling in deep learning
Maksymenko,Kostiantyn, etc.
NATURE COMMUNICATIONS, 2023, 14
Muscle electrophysiology has emerged as a powerful tool to drive human machine interfaces, with many new recent applications outside the traditional clinical domains, such as robotics and virtual reality. However, more sophisticated, functional, and robust decoding algorithms are required to meet the fine control requirements of these applications. Deep learning has shown high potential in meeting these demands, but requires a large amount of high-quality annotated data, which is expensive and time-consuming to acquire. Data augmentation using simulations, a strategy applied in other deep learning applications, has never been attempted in electromyography due to the absence of computationally efficient models. We introduce a concept of Myoelectric Digital Twin - highly realistic and fast computational model tailored for the training of deep learning algorithms. It enables simulation of arbitrary large and perfectly annotated datasets of realistic electromyography signals, allowing new approaches to muscular signal decoding, accelerating the development of human-machine interfaces.
阅读原文：https://www.nature.com/articles/s41467-023-37238-w