Train Neural Machine Translation Models with Sockeye

New on the AWS #AI Blog: Train Neural Machine Translation Models with Sockeye.

  • Sockeye, which is built on Apache MXNet, does most of the heavy lifting for building, training, and running state-of-the-art sequence-to-sequence models.
  • Sockeye provides both a state-of-the-art implementation of neural machine translation (NMT) models and a platform to conduct NMT research.
  • You can easily change the basic model architecture, including the following elements:

    Sockeye also supports more advanced features, such as:

    For training, Sockeye gives you full control over important optimization parameters.

  • If you have a GPU available, install Sockeye for CUDA 8.0 with the following command:

    To install it for CUDA 7.5, use this command:

    Now you’re all set to train your first German-to-English NMT model.

  • You also learned how to use Sockeye, a sequence-to-sequence framework based on MXNet, to train and run a minimal NMT model.

Have you ever wondered how you can use machine learning (ML) for translation? With our new framework, Sockeye, you can model machine translation (MT) and other sequence-to-sequence tasks. Sockeye, which is built on Apache MXNet, does most of the heavy lifting for building, training, and running state-of-the-art sequence-to-sequence models.
Continue reading “Train Neural Machine Translation Models with Sockeye”

Lecture Collection

Lecture Collection - Natural Language Processing with #DeepLearning (Winter 2017) [Stanford]

  • Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication.
  • This lecture series provides a thorough introduction to the cutting-edge research in deep learning applied to NLP, an approach that has recently obtained very high performance across many different NLP tasks including question answering and machine translation.

Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication. This lecture s…
Continue reading “Lecture Collection”

The app is dead. And the IoT killed it. Internet of Things blog

Jane Jetson didn't use #apps - ! #TheJetsons #IoT #AI #H2M

  • Like millions of people around the world, you may have received a shiny new device as a holiday gift at the end of last year.
  • The world has changed for the better because WE NO LONGER NEED A SEPARATE APP to use our things, the ‘things’ in the Internet of Things (IoT).
  • — @Libovness (Source)

    Text is still superior to voice, as anyone who has used Google Home or Amazon Echo (yes, I have one, and I love it) and/or tried to use voice while waiting in an airport security line without having other people overhear: 1) your proprietary business information, 2) your squeeze’s silly nickname, or 3) your holiday weight gain, can tell you.

  • , increase product usability (no apps to learn, even grandmothers can message, especially when they get to choose their own channel), and focus on what they do best (i.e., I have yet to meet a product engineer who loves managing dozens of communications platforms’ constantly changing Application Processing Interfaces (APIs)).
  • Learn more about how UIB is enabling products and software to communicate with people and things, and see the latest smart home, Industry 4.0, and smart city use cases now at unifiedinbox.com and unificationengine.com.

Ken Herron of IoT messaging company Unified Inbox, explores how the IoT means we no longer need a separate app to use our things.
Continue reading “The app is dead. And the IoT killed it. Internet of Things blog”

Top 10 Machine Learning Projects on Github

Top 10 #MachineLearning Projects on Github #KDN

  • The top 10 machine learning projects on Github include a number of libraries, frameworks, and education resources.
  • While there are many sources of such tools on the internet, Github has become a de facto clearinghouse for all types of open source software, including tools used in the data science community.
  • This is a curated list of machine learning libraries, frameworks, and software.
  • The list is categorized by language, and further by machine learning category (general purpose, computer vision, natural language processing, etc.).
  • This is a collection of IPython notebook tutorials for scikit-learn, as well as a number of links to related Python-specific and general machine learning topics, and more general data science information.


The top 10 machine learning projects on Github include a number of libraries, frameworks, and education resources. Have a look at the tools others are using, and the resources they are learning from.

Continue reading “Top 10 Machine Learning Projects on Github”

Google Sheets now uses machine learning to help you visualize your data

Google Sheets now uses machine learning to help you visualize your data  #CompBindTech

  • After adding the machine learning-powered “Explore” feature last year, which lets you ask natural language questions about your data, it’s now expanding this feature to also automatically build charts for you.
  • All of this is backed by the same natural language understanding tech that already powered the “Explore” feature.
  • It’s worth noting that the previous version of “Explore” could already build graphs for you, but those focused on your complete data set.
  • With this new version, Google also is making it easier to keep in sync data from Sheets that you use in Docs or Slides.
  • You could already update charts you copy into Docs and Slides with just a click, but now you also can do the same with tables.

Google Sheets is getting smarter today. After adding the machine learning-powered “Explore” feature last year, which lets you ask natural language questions..
Continue reading “Google Sheets now uses machine learning to help you visualize your data”

Lecture Collection

Natural Language Processing with #DeepLearning lecture videos, Manning & Socher (Stanford)

  • Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication.
  • This lecture series provides a thorough introduction to the cutting-edge research in deep learning applied to NLP, an approach that has recently obtained very high performance across many different NLP tasks including question answering and machine translation.

Natural language processing (NLP) deals with the key artificial intelligence technology of understanding complex human language communication. This lecture s…
Continue reading “Lecture Collection”