人工智能发展史论文_有史以来15篇最佳AI研究论文

人工智能发展史论文

TensorFlow：异构分布式系统上的大规模机器学习(TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems)

By Google Team

由Google团队提供

摘要—(Abstract —)

TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed with little or no change on a wide variety of heterogeneous systems, ranging from mobile devices such as phones and tablets up to large-scale distributed systems of hundreds of machines and thousands of computational devices such as GPU cards. The system is flexible and can be used to express a wide variety of algorithms, including training and inference algorithms for deep neural network models, and it has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields, including speech recognition, computer vision, robotics, information retrieval, natural language processing, geographic information extraction, and computational drug discovery. This paper describes the TensorFlow interface and an implementation of that interface that we have built at Google.

TensorFlow是用于表达机器学习算法的接口，也是用于执行此类算法的实现。 使用TensorFlow表示的计算几乎可以在多种异构系统上执行，而无需改变，范围从移动设备(如手机和平板电脑)到大型分布式系统(包括数百台机器和数千个计算设备，例如GPU卡) 。 该系统非常灵活，可用于表达各种算法，包括用于深度神经网络模型的训练和推理算法，并且已用于进行研究以及将机器学习系统部署到十几个领域的生产环境中。计算机科学和其他领域，包括语音识别，计算机视觉，机器人技术，信息检索，自然语言处理，地理信息提取和计算药物发现。 本文介绍了TensorFlow接口以及我们在Google上构建的该接口的实现。

Paper can be found here :

纸可以在这里找到：

https://arxiv.org/pdf/1603.04467v2.pdf

https://arxiv.org/pdf/1603.04467v2.pdf

Code can be found here :

代码可以在这里找到：

Scikit-learn：Python中的机器学习 (Scikit-learn: Machine Learning in Python)

By Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Andreas Müller, Joel Nothman, Gilles Louppe, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Édouard Duchesnay

由Fabian Pedregosa，GaëlVaroquaux，Alexandre Gramfort，Vincent Michel，Bertrand Thirion，Olivier Grisel，Mathieu Blondel，AndreasMüller，Joel Nothman，Gilles Louppe，Peter Prettenhofer，Ron Weiss，Vincent Dubourg，Jake Vanderplas，Alexandre Passos，David布鲁彻(Brucher)，马修(Matthieu Perrot)，爱德华·杜什奈(ÉdouardDuchesnay)

摘要— (Abstract —)

Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings.

Scikit-learn是一个Python模块，该模块集成了各种针对中型监督和非监督问题的最新机器学习算法。 该软件包致力于使用通用的高级语言将机器学习带给非专业人员。 重点放在易用性，性能，文档和API一致性上。 它具有最小的依赖关系，并根据简化的BSD许可证进行分发，从而鼓励在学术和商业环境中使用它。

Paper can be found here :

纸可以在这里找到：

https://arxiv.org/pdf/1201.0490v4.pdf

https://arxiv.org/pdf/1201.0490v4.pdf

Code can be found here :

代码可以在这里找到：

PyTorch：一种命令式风格的高性能深度学习库 (PyTorch: An Imperative Style, High-Performance Deep Learning Library)

By Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury , Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary Devito , Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, Soumith Chintala

亚当·帕斯克(Adam Paszke)，萨姆·格罗斯(Sam Gross)，弗朗西斯科·马萨(Francisco Massa)，亚当·莱勒(Adam Lerer)，詹姆斯·布拉德伯里(James Bradbury)，格里高利·南(Gregory Chanan)，特雷弗·基林(Trevor Killeen)，林明(Zeming Lin)，娜塔莉亚·吉梅尔谢因(Luca Antiga)，奥尔本·德斯麦森(Alban Desmaison)，安德烈亚斯·科普夫(Andreas Kopf)，爱德华·杨(Ecav。 Chilamkurthy，Benoit Steiner，Lu Fang，Junbai Bai，Soumith Chintala

摘要— (Abstract —)

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it was designed from first principles to support an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several commonly used benchmarks.

深度学习框架通常侧重于可用性或速度，而不是两者。 PyTorch是一个机器学习库，它表明这两个目标实际上是兼容的：它是从第一原理开始设计的，以支持命令式和Pythonic编程风格，该风格支持将代码作为模型，使调试容易并且与其他流行的科学计算库一致，同时保持高效并支持硬件加速器(例如GPU)。 在本文中，我们详细介绍了驱动PyTorch实施的原理以及它们如何反映在其体系结构中。 我们强调，PyTorch的每个方面都是受用户完全控制的常规Python程序。 我们还说明了运行时关键组件的谨慎而务实的实现方式如何使它们能够协同工作以实现出色的性能。 我们在几个常用的基准上演示了各个子系统的效率以及PyTorch的整体速度。