InfoQ Homepage QCon ai Content on InfoQ
-
Policing the Capital Markets with ML
Cliff Click talks about SCORE, a solution for doing Trade Surveillance using H2O, Machine Learning, and a whole lot of domain expertise and data munging.
/presentations/capital-markets-ml/en/mediumimage/Cliff-Click-m-1559583454114.jpg)
-
From Robot Simulation to the Real World
Louise Poubel overviews Gazebo's architecture with examples of projects using Gazebo, describing how to bridge virtual robots to their physical counterparts.
/presentations/robot-simulation-real-world/en/mediumimage/Louise-Poubel-m-1559740519445.jpg)
-
Panel: Predictive Architectures in Practice
The panelists discuss the unique challenges of building and running data architectures for predictions, recommendations and machine learning.
/presentations/panel-predictive-arch/en/mediumimage/panel-predictive-arch-m-1559579957984.jpg)
-
Papers in Production Lightning Talks
Papers: Towards a Solution to the Red Wedding Problem, A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise, and A Machine Learning Approach to Databases Indexes.
/presentations/papers-production-lighting-talk/en/mediumimage/papers-production-lighting-talk-m-1559576642650.jpg)
-
Interpretable Machine Learning Products
Mike Lee Williams discusses how interpretability can make deep neural networks models easier to understand, and describes LIME, an OS tool that can be used to explore what ML classifiers are doing.
/presentations/ml-interpretability-lime/en/mediumimage/Mikebig-1528336770231.JPG)
-
End-to-End ML without a Data Scientist
Holden Karau discusses how to train models, and how to serve them, including basic validation techniques, A/B tests, and the importance of keeping models up-to-date.
/presentations/ml-models-ab-tests/en/mediumimage/End-to-End-ML-without-Data-Scientist-ribbon-1530266022644.jpg)
-
Deep Learning for Science
Prabhat discusses machine learning's impact on climatology, astronomy, cosmology, neuroscience, genomics, and high-energy physics, and the future of AI in powering scientific discoveries.
/presentations/deep-learning-science/en/mediumimage/Prabig-1527731821296.JPG)
-
Liquidity Modeling in Real Estate Using Survival Analysis
Xinlu Huang and David Lundgren discuss hazard and survival modeling, metrics, and data censoring, describing how Opendoor uses these models to estimate holding times for homes and mitigate risk.
/presentations/liquidity-modeling-risk/en/mediumimage/Doibig-1527731396587.JPG)
-
Data Pipelines for Real-Time Fraud Prevention at Scale
Mikhail Kourjanski discusses the architecture of PayPal’s data service which combines a Big Data approach with providing data in real time for decision making in fraud detection.
/presentations/paypal-data-service-fraud/en/mediumimage/Mikbig-1527121529188.JPG)
-
pDB: Scalable Prediction Infrastructure with Precision and Provenance
Balaji Rengarajan describes the platform built on the Celect’s pDB framework, providing multiple use cases such as online personalization, document classification, and geospatial anomaly detection.
/presentations/celect-pdb/en/mediumimage/Balbig-1527086103910.JPG)
-
Self-Racing Using Deep Neural Networks: Lap 2
Jendrik Joerdening and Anthony Navarro discuss how a team of Udacity students used neural networks to teach a car to drive by itself around a track in two days.
/presentations/udacity-self-driving-ai/en/mediumimage/doibig-1527085651698.JPG)
-
The Black Swan of Perfectly Interpretable Models
Mayukh Bhaowal, Leah McGuire discuss how Salesforce Einstein made ML more transparent and less of a black box, and how they managed to drive wider adoption of ML.
/presentations/salesforce-einstein-ml/en/mediumimage/Doibig-1527036251434.JPG)