InfoQ Homepage Machine Learning Content on InfoQ
-
Automating Inventory at Stitch Fix
Sally Langford talks about the use of ML within StitchFix’s inventory forecasting system, the architecture they have developed in-house and their use of Bayesian methods.
/presentations/stitch-fix-ml/en/mediumimage/Salbig-1507251846625.jpg)
-
Solving Payment Fraud and User Security with ML
Soups Ranjan talks about Coinbase’s risk program that relies on machine learning (supervised and unsupervised), rules-based systems as well as highly-skilled human fraud fighters.
/presentations/coinbase-risk-machine-learning/en/mediumimage/Soubig-1507251574285.jpg)
-
Evaluating Machine Learning Models: A Case Study
Nelson Ray talks about on how to estimate the business impact of launching various machine learning models, in particular, those Opendoor uses for modeling the liquidity of houses.
/presentations/opendoor-machine-learning/en/mediumimage/Nelbig-1507161797360.jpg)
-
Deep Learning @Google Scale: Smart Reply in Inbox
Anjuli Kannan describes the algorithmic, scaling, deployment considerations involved in a an application of cutting-edge deep learning in a user-facing product: the Smart Reply feature of Google Inbox
/presentations/google-smart-reply/en/mediumimage/anujan-medium-1507029761562.jpg)
-
Semi-Supervised Deep Learning on Large Scale Climate Models
Prabhat presents NERSc’s results in applying Deep Learning for supervised and semi-supervised learning of extreme weather patterns, scaling Deep Learning to 9000 KNL nodes on a supercomputer.
/presentations/nerc-deep-learning/en/mediumimage/Prabig-1506561075792.JPG)
-
Architecture & Algorithms Powering Search @ZocDoc
Brian D'Alessandro and Pedro Rubio talk about the patient friendly search system they have built at Zocdoc using various products from the AWS stack and custom Machine Learning pipelines.
/presentations/zocdoc-search/en/mediumimage/Doibig.JPG)
-
When Models Go Rogue: Hard Earned Lessons on Using Machine Learning in Production
David Talby summarizes best practices & lessons learned in ML, based on nearly a decade of experience building & operating ML systems at Fortune 500 companies across several industries.
/presentations/practices-lessons-ml-systems/en/mediumimage/Davbig.JPG)
-
Large Scale Machine Learning for Payment Fraud Prevention
Venkatesh Ramanathan presents how advanced machine learning algorithms such as Deep Learning and Gradient Boosting are applied at PayPal for fraud prevention.
/presentations/paypal-ml-fraud-prevention/en/mediumimage/Venbig.JPG)
-
Build a Better Monster: Morality, Machine Learning and Mass Surveillance
Maciej Ceglowski wonders what tech companies can do to reduce the amount of data collected, closing the path to mass surveillance and bringing some morality in using ML with this data.
/presentations/morality-ml-mass-surveillance/en/mediumimage/Macbig.JPG)
-
Fast, Scalable, Reusable: A New Perspective on Production ML/AI Systems
Ekrem Aksoy discusses why production ML/AI systems should have a different perspective than the usual DevOps perspective which works on data immune systems.
/presentations/production-ml-ai-devops/en/mediumimage/Ekrbig.JPG)
-
Deep Learning for Image Understanding at Scale
Stacey Svetlichnaya discusses strategies and challenges building deep learning systems for object recognition at scale, using automatic labels in Flickr image search as a case study.
/presentations/deep-learning-image-scale/en/mediumimage/Stabig.JPG)
-
In Depth TensorFlow
Illia Polosukhin keynotes on TensorFlow, introducing it and presenting the components and concepts it is built upon.
/presentations/tensorflow-concepts/en/mediumimage/Ilibig.JPG)