November 25, 2019

128 words 1 min read

Fighting bad guys with data science

Fighting bad guys with data science

Jonathon Morgan explores computer vision, deep learning, and natural language processing techniques for uncovering communities of white nationalists and neo-Nazis on social media and identifying which ones are on the path to radicalization.
Talk Title Fighting bad guys with data science
Speakers Jonathon Morgan (New Knowledge)
Conference O’Reilly Open Source Convention
Conf Tag Making Open Work
Location Austin, Texas
Date May 8-11, 2017
URL Talk Page
Slides Talk Slides
Video

In research for a recent Washington Post article, Jonathon Morgan uncovered communities of white nationalists and neo-Nazis on social media and showed that they’ve adopted increasingly violent rhetoric over the past nine months. Jonathon explores computer vision, deep learning, and natural language processing techniques for finding these communities and identifying which ones are on the path to radicalization.

computer vision deep learning data science
comments powered by Disqus
Semantic natural language understanding at scale using Spark, machine-learned annotators, and deep-learned ontologies

Semantic natural language understanding at scale using Spark, machine-learned annotators, and deep-learned ontologies

November 2, 2019

David Talby and Claudiu Branzan offer a live demo of an end-to-end system that makes nontrivial clinical inferences from free-text patient records. Infrastructure components include Kafka, Spark Streaming, Spark, and Elasticsearch; data science components include spaCy, custom annotators, curated taxonomies, machine-learned dynamic ontologies, and real-time inferencing.
Building Distributed TensorFlow Using Both GPU and CPU on Kubernetes [I]

Building Distributed TensorFlow Using Both GPU and CPU on Kubernetes [I]

November 24, 2019

Big Data and Machine Learning have become extremely hot topics in recent years. Google has announced its AI-centric strategy and released the deep learning toolkit TensorFlow. TensorFlow soon became t …
Open source AI at AWS and Apache MXNet

Open source AI at AWS and Apache MXNet

November 22, 2019

A wide variety of open source frameworks and tools support artificial intelligence and deep learning. Adrian Cockcroft explains how AWS has packaged a number of themincluding deep learning frameworks such as Caffe, CNTK, Keras, MXNet, TensorFlow, Theano, and Torch and supporting tools like Jupyter and Anacondainto an Amazon Machine Image with optimized GPU support.
Developing a modern enterprise data strategy

Developing a modern enterprise data strategy

November 6, 2019

Big data and data science have great potential for accelerating business, but how do you reconcile the business opportunity with the sea of possible technologies? Data should serve the strategic imperatives of a businessthose aspirations that will define an organizations future vision. Scott Kurth and Edd Wilder-James explain how to create a modern data strategy that powers data-driven business.
How Lufthansa German Airlines is using data analytics to create the next level of customer experience

How Lufthansa German Airlines is using data analytics to create the next level of customer experience

November 5, 2019

The aviation industry is facing a huge pressure in costs as well as a profound disruption in marketing and service. With ticket revenues dropping, increasing customer loyalty is key. Andreas Ribbrock explains how Lufthansa German Airlines uses data science and data-driven decision making to create the next level of digital customer experience along the full customer journey.
How Microsoft predicts churn of cloud customers using deep learning and explains those predictions in an interpretable way

How Microsoft predicts churn of cloud customers using deep learning and explains those predictions in an interpretable way

November 5, 2019

Although deep learning has proved to be very powerful, few results are reported on its application to business-focused problems. Feng Zhu and Val Fontama explore how Microsoft built a deep learning-based churn predictive model and demonstrate how to explain the predictions using LIMEa novel algorithm published in KDD 2016to make the black box models more transparent and accessible.