Deploying Real Time Decision Services Using Redis
2020-02-27 87浏览
- 1.Deploying Real-Time Decision Sevices using Redis Tague Griffith, Redis Labs #MLSAIS12
- 2.Why Machine Learning
- 3.Teaching a computer, by example, an algorithm that is too complex to program
- 4.Machine Learning Problems Classification Regression Clustering Pick One of a Set Score or Rank Group Similar • Spam Detection • Manufacturing defect detection • Handwriting analysis • Decision Trees • Naïve Bayes • Logistic Regression • Recommendations • Likelihood of Purchase • Linear Regression • SVM • Find Similar Items • Customer segmentation • Cohort detection • K-Means • K-Nearest Neighbors • Hierarchical Clustering
- 5.Supervised Learning – Training Spam Classifier #MLSAIS12
- 6.Deploying a Spam Classifier #MLSAIS12
- 7.How do we Build these Boxes ¯\_( )_/¯ #MLSAIS12
- 8.• Building high performance and reliable services are hard, isn't there something we can deploy
- 9.Redis - ML
- 10.Typical Spark Application Structure Spark Training Data is loaded into Spark Model is saved in files File System Client App Custom Server Model is loaded to your custom app #MLSAIS12 Serving Client
- 11.Redis-ML:Predictive Model Serving Engine • Predictive models as native Redis types • Perform evaluation directly in Redis • Any Training Platform Store training output as “hot model” Spark Training Data loaded into Spark ClientClientClient App App App Redis-ML Model is saved in Redis-ML Serving Client
- 12.REmote DIctionary Server Strings Hashes Lists Sets Bitmaps Hyperloglogs Sorted Sets Geospatial Bitfield
- 13.A Quick Recap of Redis "I'm a Plain Text String!" {A:'>A: