Скачать или смотреть Howto Transform Research Oriented Code into Machine Learning APIs w/ Python (Tetsuya Jesse Hirata)

How to Transform Research Oriented Code into Machine Learning APIs with Python (Tetsuya Jesse Hirata) (Japan) is an English session in the online PyCon HK 2020 Spring.


Target Audience:

The audiences can be engineers, data scientists, or researchers at junior or middle level who use python.
This talk could be more beneficial for people who have experience to be involved with AI / ML projects.
One of the major things that the talk can provide could be that audiences would learn each responsibility of each role in AI / ML projects and process to implement AI / ML products, and the better or best practices of ML API implementation.

Talk Description:

Introduction

Why do I talk about this topic ? (1 minute)
The Four Steps to transform Research Oriented Code into Machine Learning APIs with Python (1 minute)

Main Talk (+ sample codes and explanations in each section)
1) Understand what code you look at and make, and how to handle the code. (6 minutes)

What is Research Oriented Code ?
What are ML APIs ?
How should engineers handle research oriented code ?

2) Modularize research oriented code (6 minutes)

Categorize research oriented code into preparation code, preprocessing code, and ML code
Break them out into functions and make them testable
Clarify input and output of the code, and define URI

3) Refactor research oriented code (6 minutes)

Prepare for refactoring by understanding requirements of each code and taking notes about them
Simplify I/O code in preparation code
Transform coding style with pandas into purely pythonic code in preprocessing code

4) Check the ML APIs can work correctly on the server (6 minutes)

Write decorators to automatically check parameters
Set up production-like environments
Suggest a tiny example of CI/CD environments for ML APIs.

Summarize the talk

Quickly review the four steps to transform Research Oriented Code into Machine Learning APIs with Python (1 minute)
Share the useful resources and tips related to what is mentioned in the talk. (1 minute)

Level: Intermediate

Speaker Bio: Tetsuya Jesse Hirata

Jesse is a software engineer based in Tokyo. He has been involved with several AI/ML projects in EdTech domain and has mainly been implementing ML APIs and ML Ops environment. Prior to this, he used to research the relationships between online learning behaviors and learning outcomes at the UCL Institute of Education (IOE) in the UK. His interest is in how to bridge the gap between data science and engineering.

https://github.com/tetsuya0617
  / tetsuya-hirata-a31b52134  
  / jessetetsuya  
  / jessetetsuya