InfoQ Homepage QCon Software Development Conference Content on InfoQ
-
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)
-
Tech in Banking Panel
The panelists discuss some of the challenges of architecting systems for banking.
/presentations/tech-banking-panel/en/mediumimage/Panbig-1527384739605.jpg)
-
FlexiTime Token: Building dApps with Ethereum
Alex Batlin talks about dApp in Ethereum, what it is and how it can help us track pre-bought time as tokens on blockchain.
/presentations/dapp-ethereum/en/mediumimage/Alexbig-1527384481770.JPG)
-
Microservices: API Re-Platforming @Expedia
Mariano Albera describes how the Expedia Affiliate Network unit underwent a massive replatforming project that moved from an on-prem monolith to a cloud-based microservice architecture.
/presentations/expedia-monolith-microservices/en/mediumimage/Mareibig-1527382683909.JPG)
-
Actors or Not: Async Event Architectures
Yaroslav Tkachenko discusses two approaches to an asynchronous event-based architecture: a "classic" style protocol and an actor-based approach, exploring benefits, challenges, and lessons learned.
/presentations/async-event-arch/en/mediumimage/Yarbig-1527382289781.JPG)
-
CRDTs and the Quest for Distributed Consistency
Martin Kleppmann explores how to ensure data consistency in distributed systems, especially in systems that don't have an authoritative leader, and peer-to-peer communication.
/presentations/crdt-distributed-consistency/en/mediumimage/Marbig-1527380291967.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)