Gradient Flow

Category: Data Science

  • Enabling enterprise adoption of AI technologies

    [A version of this post appears on the O’Reilly Radar.] The O’Reilly Data Show Podcast: Jana Eggers on building applications that rely on synaptic intelligence. Subscribe to the O’Reilly Data Show Podcast to explore the opportunities…

  • Using Agile development techniques for data science projects

    [A version of this post appears on the O’Reilly Radar.] The O’Reilly Data Show Podcast: John Akred on building data platforms and enterprise data strategies. Subscribe to the O’Reilly Data Show Podcast to explore the opportunities…

  • 3 ideas to add to your data science toolkit

    [A version of this post appears on the O’Reilly Radar.] Techniques to address overfitting, hyperparameter tuning, and model interpretability. I’m always on the lookout for ideas that can improve how I tackle data analysis projects. I…

  • Commercial speech recognition systems in the age of big data and deep learning

    [A version of this post appears on the O’Reilly Radar.] The O’Reilly Data Show Podcast: Yishay Carmiel on applications of deep learning in text and speech. Subscribe to the O’Reilly Data Show Podcast to explore the…

  • What is Artificial Intelligence?

    Mike Loukides and Ben Lorica examine factors that have made AI a hot topic in recent years, today’s successful AI systems, and where AI may be headed. By Ben Lorica and Mike Loukides. [This post originally…

  • Building intelligent applications with deep learning and TensorFlow

    [A version of this post appears on the O’Reilly Radar.] The O’Reilly Data Show Podcast: Rajat Monga on the current state of TensorFlow and training large-scale deep neural networks. Subscribe to the O’Reilly Data Show Podcast…

  • Using AI to build a comprehensive database of knowledge

    [A version of this post appears on the O’Reilly Radar.] The O’Reilly Data Show Podcast: Mike Tung on large-scale structured data extraction, intelligent systems, and the importance of knowledge databases. Subscribe to the O’Reilly Data Show…

  • Hardcore Data Science, London 2016

    The first edition of Hardcore Data Science in Europe featured 12 outstanding sessions. My co-organizer, Angie Ma of ASI deserves much of the credit for recruiting many of the speakers. We had talks on machine learning…

  • Structured streaming comes to Apache Spark 2.0

    [A version of this post appears on the O’Reilly Radar.] The O’Reilly Data Show Podcast: Michael Armbrust on enabling users to perform streaming analytics, without having to reason about streaming. Subscribe to the O’Reilly Data Show…

  • Don’t overlook simpler techniques and algorithms

    Even in areas and domains where deep learning excels, simpler approaches are worth examining. A while back I noted that there are several considerations when evaluating machine learning models: Accuracy is the main objective and a…