Completed
Patterns of software choices Reprint Four patterns of the workflow regarding combination of Model Development phase and Model Operating phase
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Lessons Learned from Big Data and AI/ML Collaboration for Giant Hogweed Eradication
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Self introduction
- 3 Outline
- 4 Our journey to apply deep learning for giant hogweed eradication
- 5 About giant hogweed
- 6 Project Overview
- 7 Data volumes
- 8 Various specialty
- 9 Challenges of the project
- 10 Architecture overview
- 11 Data flow-1/4: Data preparation phase
- 12 Assistance tool for data preparation
- 13 Inference processing by Apache Spark
- 14 Data flow-4/4: Data analysis phase
- 15 Lessons Learned from a consideration of architecture design
- 16 Common view in Machine learning system
- 17 Scaled-ML systems
- 18 ML Application with scalability on our architecture
- 19 Model development vs. Model operating
- 20 Dev-friendly to Dev-friendly
- 21 Dev-friendly to Ops-friendly
- 22 Use case: Uber implemented ML Ops on Spark
- 23 Ops-friendly to Ops-friendly Patterns that selected a toolset familiar to Model Operator for both model development and operation
- 24 Use case: Twitter leveraged Scala for feature engineering
- 25 Example software: BigDL by Intel
- 26 Patterns of software choices Reprint Four patterns of the workflow regarding combination of Model Development phase and Model Operating phase
- 27 Architecture and data pipeline ver.2.0
- 28 Tips: Abstraction of functions used in applications
- 29 Tips: Detecting and storing deterioration of confidence