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
    Snowflake 
    • 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

    Comments

    Post a Comment

    Popular posts from this blog

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

    Image
    The Windows Subsystem for Linux operates as a virtual machine that can dynamically grow the amount of RAM to a maximum set at startup time.  Microsoft sets a default maximum RAM available to 50% of the physical memory and a swap-space that is 1/4 of the maximum WSL RAM.  You can scale those numbers up or down to allocate more or less RAM to the Linux instance. The first drawing shows the default WSL memory and swap space sizing. The images below show a developer machine that is running a dev environment in WSL2 and Docker Desktop.  Docker Desktop has two of its own WSL modules that need to be accounted for.  You can see that the memory would actually be oversubscribed, 3 x 50% if every VM used its maximum memory.  The actual amount of memory used is significantly smaller allowing every piece to fit. Click to Enlarge The second drawing shows the memory allocation on my 64GB laptop. WSL Linux defaults to a maximum RAM size of 5
    Read more

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

    Image
    I do a lot of my development and configuration via ssh into my Raspberry Pi Zero over the RNDIS connection. Some models of the Raspberry PIs can be configured with  gadget drivers  that let the Raspberry pi emulate different devices when plugged into computers via USB. My favorite gadget  is the network profile that makes a Raspberry Pi look like an RNDIS-attached network device.  All types of network services travel over an RNDIS device without knowing it is a USB hardware connection. A Raspberry Pi shows up as a Remote NDIS (RNDIS) device when you plug the Pi into a PC or Mac via a USB cable. The gadget  in the Windows Device Manager picture shows this RNDIS Gadget connectivity between a Windows machine and a Raspberry Pi. The Problem Windows 11 and Windows 10 no longer auto-installs the RNDIS driver that makes magic happen. Windows recognizes that the Raspberry Pi is some type of generic USB COM device. Manually running W indows Update  or  Update Driver  does  not  install the RNDI
    Read more

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

    Image
    I wanted to access all my Azure resources without making any of them visible to the Internet.   The easiest give my local machine access to everything on my Azure Virtual Network (VNET) was to connect to it over VPN. It turns out creating Azure VPN gateways and connecting to Azure VPN endpoints is easy.  There are some subtleties in getting DNS name resolution to work that can confuse when first starting out. Setting the Stage There are a few ways to get to Azure endpoints and resources that are blocked from the internet.  We can  Create a Point-to-Site connection from our local machines to Azure Network Gateways Create a Site-to-Site network connection from our local networks to Azure Network Gateways. Use Bastion Hosts Use Cloud Shell Leave everything open to the internet. I chose a Point-to-Site (P2S) VPN connection that connects from my laptop to a VNet Gateway.  That joins my laptop
    Read more