Об этом курсе: You will learn how to build a successful machine learning project. If you aspire to be a technical leader in AI, and know how to set direction for your team's work, this course will show you how. Much of this content has never been taught elsewhere, and is drawn from my experience building and shipping many deep learning products. This course also has two "flight simulators" that let you practice decision-making as a machine learning project leader. This provides "industry experience" that you might otherwise get only after years of ML work experience. After 2 weeks, you will: - Understand how to diagnose errors in a machine learning system, and - Be able to prioritize the most promising directions for reducing error - Understand complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance - Know how to apply end-to-end learning, transfer learning, and multi-task learning I've seen teams waste months or years through not understanding the principles taught in this course. I hope this two week course will save you months of time. This is a standalone course, and you can take this so long as you have basic machine learning knowledge. This is the third course in the Deep Learning Specialization.
Для кого этот курс: Pre-requisites: - This course is aimed at individuals with basic knowledge of machine learning, who want to know how to set technical direction and prioritization for their work. - It is recommended that you take course one and two of this specialization (Neural Networks and Deep Learning, and Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization) prior to beginning this course.
Преподаватели: Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
Преподаватели: Head Teaching Assistant - Kian Katanforoosh, Adjunct Lecturer at Stanford University, deeplearning.ai, Ecole Centrale Paris
Преподаватели: Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| Основные сведения | Course 3 of 5 in the Deep Learning Specialization |
| Уровень | Начинающий |
| Выполнение | 2 weeks of study, 3-4 hours/week |
| Язык | English, Субтитры: Korean, Chinese (Traditional), Chinese (Simplified) |
| Требования к аппаратным средствам | None currently, unless you'd like to download Jupyter Notebooks locally for offline work. |
| Как пройти курс | Чтобы пройти курс, выполните все оцениваемые задания. |
| Оценки пользователей |
- Видео: Orthogonalization
- Видео: Single number evaluation metric
- Видео: Satisficing and Optimizing metric
- Видео: Train/dev/test distributions
- Видео: Size of the dev and test sets
- Видео: When to change dev/test sets and metrics
- Видео: Why human-level performance?
- Видео: Avoidable bias
- Видео: Understanding human-level performance
- Видео: Surpassing human-level performance
- Видео: Improving your model performance
- Материал для самостоятельного изучения: Machine Learning flight simulator
- Видео: Andrej Karpathy interview
- Видео: Cleaning up incorrectly labeled data
- Видео: Build your first system quickly, then iterate
- Видео: Training and testing on different distributions
- Видео: Bias and Variance with mismatched data distributions
- Видео: Addressing data mismatch
- Видео: Transfer learning
- Видео: Multi-task learning
- Видео: What is end-to-end deep learning?
- Видео: Whether to use end-to-end deep learning
- Видео: Ruslan Salakhutdinov interview
Каждый курс — это интерактивный учебник, который содержит видеоматериалы, тесты и проекты.
Общайтесь с тысячами других учащихся: обсуждайте идеи, материалы курса и помогайте друг другу осваивать новые понятия.
Получите документы о прохождении курсов и поделитесь своим успехом с друзьями, коллегами и работодателями.
| Приобрести курс | |
|---|---|
| Получить доступ к материалам курса | Доступен |
| Получить доступ к оцениваемым материалам курса | Доступен |
| Получить итоговую оценку | Доступен |
| Earn a shareable Course Certificate | Доступен |
a lot of real world questions are explained! awesome!!!
Though we learn different machine learning models to train, we might miss the logical key practices and struggle and waste lot of time while training to achieve better results. This course teaches those important practices to efficiently implement the ML projects.
Covers some interesting points, particularly around introducing external data to your training set that doesn't match the distribution of the dev/test sets. Andrew Ng offers practical advice for running projects using Deep Learning techniques and how they differ from traditional approaches.
very practical :)