AWS Sagemaker Autopilot enables ML as a commodity

Two Parts

  1. ML for the masses
  2. Covid Intake ML demonstration from 2021 Snowflake Summit

Accelerating the ML revolution

Sagemaker Autopilot is moving ML from custom programming to a commodity service

  • The end of the need for Custom ML platforms
  • ML for the masses with less investment and startup costs
  • Easy access to open data
  • Partner data sharing with manageable risk

Snowflake and AWS Sagemaker Autopilot

Snowflake and AWS provided a low code demonstration that merged public health data with intake surveys to create a set of Machine model-based services that could help prioritize covid intake patients based on past patterns.  

The truly interesting part of the demonstration is that they

  1. Restructured and merged data sets inside Snowflake with simple SQL
  2. Create a full ML environment
  3. Created and trained a model
  4. Deployed the model as an endpoint
  5. Demonstrated using the model via remote API call.

    AWS Autopilot
    • determine the best model type
    • Tune hyperparameters
    • create model
    • deploy as a web service
    • public data mart
    • external functions
    • custom serializers 

    Video - What and Why

    Data, Machine Learning Training, Model Execution

    The demonstration combines public health data with other attributes to create a single feature set.  That feature set is fed to a model training environment to create a machine model.  The model is deployed as a web service.  The model is then asked for recommendations as new intake data comes in. The intake recommendations are stored in a data table. All of the actions are initiated from inside Snowflake.

    Problem Solving demonstration Flow

    These are the actual steps taken in the demonstration.  The left column contains the major steps. The right column contains details to better understand parameters and constraints.

    Video: How - the Steps


    Popular posts from this blog

    Understanding your WSL2 RAM and swap - Changing the default 50%-25%

    Installing the RNDIS driver on Windows 11 to use USB Raspberry Pi as network attached

    DNS for Azure Point to Site (P2S) VPN - getting the internal IPs