AutoML - bobbae/gcp GitHub Wiki

AutoML is a general term describing automated AI driven methods to enhance ML application and processes. AutoML is also name used by multiple projects and companies in different contexts and cloud based services.

Google Cloud AutoML helps you build custom machine learning models with limited machine learning expertise needed.

https://cloud.google.com/automl

AI Platform with AutoML

AI Platform brings AutoML and AI Platform (Classic) together into a unified API, client library, and user interface.

https://cloud.google.com/vertex-ai/docs

AutoML Vision

Derive insights from your images in the cloud or at the edge with AutoML Vision or use pre-trained Vision API models to detect emotion, understand text, and more.

https://cloud.google.com/vision/automl/docs

AutoML Vision enables you to train machine learning models to classify your images according to your own defined labels.

AutoML Vision Edge allows you to export your custom trained models.

https://cloud.google.com/vision/automl/docs#videos

AutoML Video intelligence

Video Intelligence includes several options that you can use to integrate machine learning video intelligence models into your applications.

AutoML Natural Language

AutoML Natural Language enables you to build and deploy custom machine learning models that analyze documents, categorizing them, identify entities within them, or assessing attitudes within them.

AutoML Translation

AutoML Translation lets you to create your own translation models so that translation queries return results specific to your domain.

Cloud Translation - Advanced is part of the Cloud Translation service that provides support for glossaries, batch requests, and AutoML models.

AutoML Tables

AutoML Tables helps to build and deploy machine learning models on structured data at speed and scale.

AutoML Tables help you create clean, effective training data by providing information about missing data, correlation, cardinality, and distribution for each of your features.

AutoML Feature Engineering

When you kick off training, AutoML Tables automatically performs common feature engineering tasks for you, including:

Normalize and bucketize numeric features.
Create one-hot encoding and embeddings for categorical features.
Perform basic processing for text features.
Extract date- and time-related features from Timestamp columns.

Data Prepping

https://developers.google.com/machine-learning/data-prep

Model training

When you kick off training for your model, AutoML Tables takes your dataset and starts training for multiple model architectures at the same time. This approach enables AutoML Tables to determine the best model architecture for your data quickly, without having to serially iterate over the many possible model architectures.

Using AutoML Tables from BigQuery

You can use AutoML Tables directly from BigQuery SQL.

https://towardsdatascience.com/the-best-of-both-worlds-calling-auto-ml-from-bigquery-9dfd433a45d6

Choosing between AutoML Tables and BigQueryML

You might want to use BigQuery ML if you are more focused on rapid experimentation or iteration with what data to include in the model and want to use simpler model types for this purpose, such as logistic regression.

You might want to work directly in the AutoML Tables interface if you have already finalized the data, and you are optimizing for maximizing model quality.

Transparency and Logging

You can view the structure of your AutoML Tables model using Cloud Logging.

Using Cloud Logging to view AutoML Tables model

Using Cloud Logging, you can see the final model hyperparameters as well as the hyperparameters and object values used during model training and tuning.

AutoML Tables model logs have, among other fields: