Об этом курсе: Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of data science problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way that supports experimentation. Course Objectives: Identify why deep learning is currently popular Optimize and evaluate models using loss functions and performance metrics Mitigate common problems that arise in machine learning Create repeatable and scalable training, evaluation, and test datasets
Для кого этот курс: This course is aimed at data scientists, data engineers and programmers interested in learning how to apply machine learning in practice.
Автор: Google Cloud
| Основные сведения | |
| Уровень | Учащийся среднего уровня |
| Выполнение | 5 - 7 hours per week |
| Язык | English, Субтитры: French, Portuguese (Brazilian), German, Spanish, Japanese |
| Требования к аппаратным средствам | You'll need to use a desktop web browser to access labs. |
| Как пройти курс | Чтобы пройти курс, выполните все оцениваемые задания. |
| Оценки пользователей |
Просмотреть
Программа курса
НЕДЕЛЯ 1
Introduction
In this course you’ll get foundational ML knowledge so that you understand the terminology that we use throughout the specialization. You will also learn practical tips and pitfalls from ML practitioners here at Google and walk away with the code and the knowledge to bootstrap your own ML models.
2 видео
- Видео: Intro to Qwiklabs
Practical ML
In this module, we will introduce some of the main types of machine learning and review the history of ML leading up to the state of the art so that you can accelerate your growth as an ML practitioner.
10 видео
- Видео: Supervised Learning
- Видео: Regression and Classification
- Видео: Short History of ML: Linear Regression
- Видео: Short History of ML: Perceptron
- Видео: Short History of ML: Neural Networks
- Видео: Short History of ML: Decision Trees
- Видео: Short History of ML: Kernel Methods
- Видео: Short History of ML: Random Forests
- Видео: Short History of ML: Modern Neural Networks
- Discussion Prompt: Modern Neural Networks
Оцениваемый: Module Quiz
Optimization
In this module we will walk you through how to optimize your ML models.
13 видео
- Видео: Defining ML Models
- Видео: Introducing the Natality Dataset
- Видео: Introducing Loss Functions
- Видео: Gradient Descent
- Видео: Troubleshooting a Loss Curve
- Видео: ML Model Pitfalls
- Видео: Lab: Introducing the TensorFlow Playground
- Видео: Lab: TensorFlow Playground - Advanced
- Видео: Lab: Practicing with Neural Networks
- Видео: Loss Curve Troubleshooting
- Видео: Performance Metrics
- Видео: Confusion Matrix
Оцениваемый: Module Quiz
Generalization and Sampling
Now it’s 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.
9 видео
- Видео: Generalization and ML Models
- Видео: When to Stop Model Training
- Видео: Creating Repeatable Samples in BigQuery
- Видео: Demo: Splitting Datasets in BigQuery
- Видео: Lab Introduction
- Видео: Lab Solution Walkthrough
- Видео: Lab Introduction
- Видео: Lab Solution Walkthrough
Оцениваемый: Lab: Creating Repeatable Dataset Splits in BigQuery
Оцениваемый: Lab: Exploring and Creating ML Datasets
Оцениваемый: Module Quiz
Summary
1 видео
Часто задаваемые вопросы
Как это работает
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Авторы
Google Cloud
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Стоимость
| Приобрести курс | |
|---|---|
| Получить доступ к материалам курса | Доступен |
| Получить доступ к оцениваемым материалам курса | Доступен |
| Получить итоговую оценку | Доступен |
| Получите сертификат о прохождении курса, ссылкой на который можно делиться с другими людьми | Доступен |
Рейтинги и отзывы
Fluent flow of introduction using examples. Gives an overview of the ML process concepts and tips. Detailed concepts are only mentioned quickly, so to fully benefit from the course would probably require some prior experience in ML. Valuable insights and summary from experienced ML engineer are provided in this course.
Nice course. Starting from basics showing concepts clearly. I really liked it.
A good introduction to the process. Well structured. In particular I liked the section on loss functions.
Coursera делает лучшее в мире образование доступным каждому, предлагая онлайн-курсы от ведущих университетов и организаций.
© Coursera Inc., 2018 Все права защищены.
A very good introduction to ML and to important tools to use on the creating and tuning and optimization of ML models.
Thank you.