变分量子本层（VQE）是一种领先的策略，可利用嘈杂的中间量子量子（NISQ）机器来解决化学问题的表现优于经典方法。为了获得大规模问题的计算优势，可行的解决方案是量子分布式优化（QUDIO）方案，该方案将原始问题分配到$ K $子问题中，并将其分配给$ K $量子机器，然后将其分配给并行优化。尽管有可证明的加速度比率，但Qudio的效率可能会因同步操作而大大降低。为了征服这个问题，我们在这里提议在量子分布式优化期间，将洗牌措施涉及到当地的汉密尔顿人。与Qudio相比，Shuffle-Qudio显着降低了量子处理器之间的通信频率，并同时达到了更好的训练性。特别是，我们证明，Shuffle-Qudio可以比Qudio更快地收敛速率。进行了广泛的数值实验，以验证估计分子的基态能量的任务中，隔离式时间速度允许壁式时间速度和低近似误差。我们从经验上证明，我们的建议可以与其他加速技术（例如操作员分组）无缝集成，以进一步提高VQE的疗效。

量子系统的许多基本属性都被其哈密顿和基态捕获。尽管基态制备（GSP）具有重要意义，但对于大规模的哈密顿人来说，这项任务在经典上是棘手的。发挥现代量子机的力量的量子神经网络（QNN）已成为征服此问题的领先协议。因此，如何增强QNN的性能成为GSP中的关键主题。经验证据表明，具有手工对称的Ansatzes的QNN通常比不对称Ansatzes的QNN具有更好的训练性，而理论解释却没有被探索。为了填补这一知识差距，我们在这里提出了有效的量子神经切线核（EQNTK），并将这一概念与过度参数化理论联系起来，以量化QNNS趋向全球最佳OPTA的融合。我们发现，对称Ansatzes的进步归因于其较大的EQNTK值，其有效尺寸很小，这要求很少的参数和量子电路深度达到过度参数化的制度，允许良性损失景观和快速收敛。在EQNTK的指导下，我们进一步设计了一种对称修剪（SP）方案，可以自动从过度参数化和不对称的对称的ANSATZ量身定制对称的ANSATZ，以极大地提高QNN的性能，而汉密尔顿的显式对称信息是不可用的。进行了广泛的数值模拟，以验证EQNTK的分析结果和SP的有效性。

尖峰神经网络（SNN）引起了脑启发的人工智能和计算神经科学的广泛关注。它们可用于在多个尺度上模拟大脑中的生物信息处理。更重要的是，SNN是适当的抽象水平，可以将大脑和认知的灵感带入人工智能。在本文中，我们介绍了脑启发的认知智力引擎（Braincog），用于创建脑启发的AI和脑模拟模型。 Braincog将不同类型的尖峰神经元模型，学习规则，大脑区域等作为平台提供的重要模块。基于这些易于使用的模块，BrainCog支持各种受脑启发的认知功能，包括感知和学习，决策，知识表示和推理，运动控制和社会认知。这些受脑启发的AI模型已在各种受监督，无监督和强化学习任务上有效验证，并且可以用来使AI模型具有多种受脑启发的认知功能。为了进行大脑模拟，Braincog实现了决策，工作记忆，神经回路的结构模拟以及小鼠大脑，猕猴大脑和人脑的整个大脑结构模拟的功能模拟。一个名为BORN的AI引擎是基于Braincog开发的，它演示了如何将Braincog的组件集成并用于构建AI模型和应用。为了使科学追求解码生物智能的性质并创建AI，Braincog旨在提供必要且易于使用的构件，并提供基础设施支持，以开发基于脑部的尖峰神经网络AI，并模拟认知大脑在多个尺度上。可以在https://github.com/braincog-x上找到Braincog的在线存储库。

生物医学问题的回答旨在从生物医学领域获得对给定问题的答案。由于其对生物医学领域知识的需求很高，因此模型很难从有限的培训数据中学习域知识。我们提出了一种上下文嵌入方法，该方法结合了在生物医学域数据上预先训练的开放域QA模型\ AOA和\ biobert模型。我们对大型生物医学语料库采用无监督的预培训，并在生物医学问题答案数据集上进行了微调。此外，我们采用基于MLP的模型加权层自动利用两个模型的优势以提供正确的答案。由PubMed语料库构建的公共数据集\ BIOMRC用于评估我们的方法。实验结果表明，我们的模型以大幅度优于最先进的系统。

量子计算机是下一代设备，有望执行超出古典计算机范围的计算。实现这一目标的主要方法是通过量子机学习，尤其是量子生成学习。由于量子力学的固有概率性质，因此可以合理地假设量子生成学习模型（QGLM）可能会超过其经典对应物。因此，QGLM正在从量子物理和计算机科学社区中受到越来越多的关注，在这些QGLM中，可以在近期量子机上有效实施各种QGLM，并提出了潜在的计算优势。在本文中，我们从机器学习的角度回顾了QGLM的当前进度。特别是，我们解释了这些QGLM，涵盖了量子电路出生的机器，量子生成的对抗网络，量子玻尔兹曼机器和量子自动编码器，作为经典生成学习模型的量子扩展。在这种情况下，我们探讨了它们的内在关系及其根本差异。我们进一步总结了QGLM在常规机器学习任务和量子物理学中的潜在应用。最后，我们讨论了QGLM的挑战和进一步研究指示。

量子力学的内在概率性质引起了设计量子生成学习模型（QGLM）的努力。尽管取得了经验成就，但QGLMS的基础和潜在优势仍然在很大程度上晦涩难懂。为了缩小这一知识差距，我们在这里探索QGLM的概括属性，即将模型从学习的数据扩展到未知数据的能力。我们考虑两个典型的QGLM，量子电路出生的机器和量子生成的对抗网络，并明确地给出了它们的概括界限。当量子设备可以直接访问目标分布并采用量子内核时，结果确定了QGLM的优势而不是经典方法。我们进一步采用这些泛化范围来在量子状态制备和哈密顿学习中具有潜在的优势。 QGLM在加载高斯分布和估计参数化的哈密顿量的基态方面的数值结果符合理论分析。我们的工作开辟了途径，以定量了解量子生成学习模型的力量。

Recent studies have shown that using an external Language Model (LM) benefits the end-to-end Automatic Speech Recognition (ASR). However, predicting tokens that appear less frequently in the training set is still quite challenging. The long-tail prediction problems have been widely studied in many applications, but only been addressed by a few studies for ASR and LMs. In this paper, we propose a new memory augmented lookup dictionary based Transformer architecture for LM. The newly introduced lookup dictionary incorporates rich contextual information in training set, which is vital to correctly predict long-tail tokens. With intensive experiments on Chinese and English data sets, our proposed method is proved to outperform the baseline Transformer LM by a great margin on both word/character error rate and tail tokens error rate. This is achieved without impact on the decoding efficiency. Overall, we demonstrate the effectiveness of our proposed method in boosting the ASR decoding performance, especially for long-tail tokens.

Modern mobile burst photography pipelines capture and merge a short sequence of frames to recover an enhanced image, but often disregard the 3D nature of the scene they capture, treating pixel motion between images as a 2D aggregation problem. We show that in a "long-burst", forty-two 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. To this end, we devise a test-time optimization approach that fits a neural RGB-D representation to long-burst data and simultaneously estimates scene depth and camera motion. Our plane plus depth model is trained end-to-end, and performs coarse-to-fine refinement by controlling which multi-resolution volume features the network has access to at what time during training. We validate the method experimentally, and demonstrate geometrically accurate depth reconstructions with no additional hardware or separate data pre-processing and pose-estimation steps.

We propose a new neural network design paradigm Reversible Column Network (RevCol). The main body of RevCol is composed of multiple copies of subnetworks, named columns respectively, between which multi-level reversible connections are employed. Such architectural scheme attributes RevCol very different behavior from conventional networks: during forward propagation, features in RevCol are learned to be gradually disentangled when passing through each column, whose total information is maintained rather than compressed or discarded as other network does. Our experiments suggest that CNN-style RevCol models can achieve very competitive performances on multiple computer vision tasks such as image classification, object detection and semantic segmentation, especially with large parameter budget and large dataset. For example, after ImageNet-22K pre-training, RevCol-XL obtains 88.2% ImageNet-1K accuracy. Given more pre-training data, our largest model RevCol-H reaches 90.0% on ImageNet-1K, 63.8% APbox on COCO detection minival set, 61.0% mIoU on ADE20k segmentation. To our knowledge, it is the best COCO detection and ADE20k segmentation result among pure (static) CNN models. Moreover, as a general macro architecture fashion, RevCol can also be introduced into transformers or other neural networks, which is demonstrated to improve the performances in both computer vision and NLP tasks. We release code and models at https://github.com/megvii-research/RevCol

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.