深度学习:为入门者打造的前十资源

深度学习(DL)是基于人工神经网络的机器学习的一个子集。DL可以是监督,半监督或无监督形态,并且已经在医疗保健,金融,游戏,客户服务,零售等行业取得了成功。 DL的想法早在1940年就诞生了,是在1943年,由沃尔特·皮特和沃伦·麦卡洛克建立背神经网络的第一个数学模型,这些方法都随着人工智能在各个行业中展露,对现实世界带来了有益影响。在寻求解决挑战时,DL技术正变得越来越受欢迎。 作为一个由谷歌等人领导的协作社区,开源是非常有用和流行的工具。如果你在AI工作并且已经有了坚实的基础,你可能会关注DL模型。 以下是我们深度学习入门的十大资源:

  1. Deep Learning Courses, Coursera
    "In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing."
    Founded by Andrew Ng and Daphne Koller, Coursera is an online learning platform offering some of the leading courses available online. 
  2. Deep Learning, by Ian Goodfellow, Yoshua Bengio and Aaron Courville
    An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives.
    Ian, Yoshua and Aaron have all spoken at RE•WORK summits and you can watch videos of their presentations and interviews on our YouTube channel as a bonus resource!
  3. Practical Deep Learning for Coders
    To do this course, all you need is to have been coding for at least a year and to have a GPU and appropriate software. he course is video based and will run you through each session step by step. "You don’t need much data, you don’t need university-level math, and you don’t need a giant data center."
  4. An Introduction to PyTorch – A Simple yet Powerful Deep Learning Library
    "Every once in a while, a python library is developed that has the potential of changing the landscape in the field of deep learning. PyTorch is one such library."
    This article takes a hands on approach to PyTorch covering the basics, and also providing case studies. Whilst this article assumes that you have a basic understanding of DL, it provides additional resources for complete beginners. 
  5. YouTube Deep Learning Playlist
    With presentations, interviews and fireside chats from some of the global leaders in the space, this free resource brings together some of the most cutting edge research and applications of deep learning. Watch videos from Yoshua Bengio, Yann LeCun, Geoffrey Hinton, Andrew Ng, Chelsea Finn, Ian Goodfellow and more. 
  6. TensorFlow
    If you haven't used TensorFlow before, now is the time to get started."TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications." It allows you to build and train DL models easily, train and deploy them on the cloud, on device or in the browser in a variety of languages, and is a simple and flexible architecture. 
  7. Deep Learning Summer School Talks
    "Deep neural networks are a powerful method for automatically learning distributed representations at multiple levels of abstraction. Over the past decade, they have dramatically pushed forward the state-of-the-art in domains as diverse as vision, language understanding, robotics, game playing, graphics, health care, and genomics. The Deep Learning Summer School (DLSS) covers both the foundations and applications of deep neural networks, from fundamental concepts to cutting-edge research results."
    These free videos are from events hosted by the Canadian Institute for Advances Research (CIFAR) and the Vector Institute.
  8. Information Theory of Deep Learning. Naftali Tishby
    YouTube video: The workshop aims at bringing together leading scientists in deep learning and related areas within machine learning, artificial intelligence, mathematics, statistics, and neuroscience. No formal submission is required. Participants are invited to present their recently published work as well as work in progress, and to share their vision and perspectives for the field.
  9. Social Networks and Communities
    There's a lot to be said about the likes of GitHubQuora, and LinkedIn groups. As previously mentioned, the DL world is a collaborative one, and experts and beginners alike are constantly striving to help each other as well as improve their own models. 
  10. arXiv.org, Deep Learning
    Of the 1,557,544 e-prints available on arXiv, there are 16,355 DL papers. arXiv is owned and operated by Cornell University, a private not-for-profit educational institution. arXiv is funded by Cornell University, the Simons Foundation and by the member institutions.

Interested in a more hands on approach to Deep Learning? Join us in the Global Deep Learning Summit series, where we bring together leading experts in the filed to share their most cutting edge work and research progressions, exploring how it is impacting society.

RE•WORK
RE•WORK

RE•WORK成立于2013年,宗旨为促进国际人工智慧及相关之研究,发展,应用及交流。迄今为止,RE•WORK在世界各地已创办超过50场人工智能高峰会,包括新加坡,香港,美国,伦敦,加拿大等等。

入门深度学习
4
相关数据
Ian Goodfellow人物

Ian Goodfellow 是机器学习领域备受关注的年轻学者之一,他在本科与硕士就读于斯坦福大学,师从吴恩达,博士阶段则跟随蒙特利尔大学的著名学者Yoshua Bengio研究机器学习。Goodfellow 最引人注目的成就是在2014年6月提出了生成对抗网络(GAN)。这一技术近年来已成为机器学习界最火热的讨论话题,特别是在最近几个月里,与GAN有关的论文不断涌现。GAN已成为众多学者的研究方向。

Dropout技术

神经网络训练中防止过拟合的一种技术

TensorFlow技术

TensorFlow是一个开源软件库,用于各种感知和语言理解任务的机器学习。目前被50个团队用于研究和生产许多Google商业产品,如语音识别、Gmail、Google 相册和搜索,其中许多产品曾使用过其前任软件DistBelief。

推荐文章
暂无评论
暂无评论~