Launching into Machine Learning

Google Cloud via Coursera

Coursera based on 4,327 ratings

Likes

Overview

Launching into Machine Learning is an introductory course designed to guide beginners through the foundational concepts and practical steps needed to start working with machine learning. Ideal for students, professionals, or anyone curious about AI, this course demystifies key principles such as supervised and unsupervised learning, model training, and evaluation. Learners will explore essential algorithms including linear regression, decision trees, and clustering techniques, gaining hands-on experience using popular tools and libraries like Python’s Scikit-learn. The course emphasizes understanding data preparation, feature...

Syllabus

Introduction

This module provides an overview of the course and its objectives.

Get to Know Your Data: Improve Data through Exploratory Data Analysis

In this module, we look at how to improve the quality of our data and how to explore our data by performing exploratory data analysis. We look at the importance of tidy data in Machine Learning and show how it impacts data quality. For example, missing values can skew our results. You will also learn the importance of exploring your data. Once we have the data tidy, you will then perform exploratory data analysis on the dataset.

Machine Learning in Practice

In this module, we will introduce some of the main types of machine learning so that you can accelerate your growth as an ML practitioner.

Training AutoML Models Using Vertex AI

In this module, we will introduce training AutoML Models using Vertex AI.

BigQuery Machine Learning: Develop ML Models Where Your Data Lives

In this module, we will introduce BigQuery ML and its capabilities.

Optimization

In this module we will walk you through how to optimize your ML models.

Generalization and Sampling

Now its time to answer a rather weird question: when is the most accurate ML model not the right one to pick? As we hinted at in the last module on Optimization -- simply because a model has a loss metric of 0 for your training dataset does not mean it will perform well on new data in the real world. You will learn how to create repeatable training, evaluation, and test datasets and establish performance benchmarks.