The course begins with a discussion about data: how to improve data quality and perform exploratory data analysis. We describe Vertex AI AutoML and how to build, train, and deploy an ML model without writing a single line of code. You will understand the benefits of Big Query ML. We then discuss how to optimize a machine learning (ML) model and how generalization and sampling can help assess the quality of ML models for custom training.
Launching into Machine Learning
Google via Google Cloud Skills Boost
This course may be unavailable.
Overview
Syllabus
- Introduction
- Course introduction
- Get to Know Your Data: Improve Data through Exploratory Data Analysis
- Introduction
- Improve data quality
- Lab intro: Improve the quality of your data
- Lab Demo: Improve the quality of your data
- Improving Data Quality
- What is exploratory data analysis?
- How is EDA used in machine learning?
- Data analysis and visualization
- Lab intro: Explore the data using Python and BigQuery
- Exploratory Data Analysis Using Python and BigQuery
- Quiz: Get to know your data: Improve data through Exploratory Data Analysis
- Machine Learning in Practice
- Introduction
- Supervised learning
- Linear regression
- Lab intro: Introduction to linear regression
- Lab Demo: Intro to Linear Regression
- Introduction to Linear Regression
- Logistic regression
- Quiz: Machine Learning in Practice
- Training AutoML Models Using Vertex AI
- Introduction
- Machine learning vs. deep learning
- What is automated machine learning?
- AutoML regression model
- (Optional) Lab intro: Training an AutoML classification model (Structured data)
- (Optional) Lab Demo: Training an AutoML classification model (Structured data)
- Training an AutoML Classification Model - Structured Data
- Evaluate AutoML models
- Quiz: Training AutoML Models Using Vertex AI
- BigQuery Machine Learning: Develop ML Models Where Your Data Lives
- Introduction
- Training an ML model using BigQuery ML
- BigQuery Machine Learning supported models
- Lab intro: Using BigQuery ML to predict penguin weight (BigQuery ML & Explainable AI)
- Lab Demo: Using BigQuery ML to predict penguin weight (BigQuery ML & Explainable AI)
- Using BigQuery ML to Predict Penguin Weight
- BigQuery ML hyperparameter tuning
- (Optional) Lab intro: Using the BigQuery ML hyperparameter tuning to improve model performance
- Using the BigQuery ML Hyperparameter Tuning to Improve Model Performance
- How to build and deploy a recommendation system with BigQuery ML
- Quiz: BigQuery Machine Learning: Develop ML Models Where Your Data Lives
- Optimization
- Introduction
- Defining ML models
- Introducing the course dataset
- Introduction to loss functions
- Gradient descent
- Troubleshooting loss curves
- ML model pitfalls
- Lecture lab: Introducing the TensorFlow Playground
- Lecture lab: TensorFlow Playground - Advanced
- Lecture lab: Practicing with neural networks
- Performance metrics
- Confusion matrix
- Quiz: Optimization
- Generalization and Sampling
- Introduction
- Generalization and ML models
- When to stop model training
- Creating repeatable samples in BigQuery
- Demo: Splitting datasets in BigQuery
- Quiz: Generalization and Sampling
- Summary
- Summary
- Resource: All quiz questions
- Resource: All readings
- Resource: All slides
