关于此课程： 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.
此课程适用人群： 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.
教学方： Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
教学方： Head Teaching Assistant - Kian Katanforoosh, Lecturer of Computer Science at Stanford University, deeplearning.ai, Ecole CentraleSupelec
教学方： Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| 基本信息 | 课程 3（共 5 门，Deep Learning Specialization ） |
| 级别 | 初级 |
| 承诺学习时间 | 2 weeks of study, 3-4 hours/week |
| 语言 | English, 字幕： Chinese (Traditional), Chinese (Simplified), Korean, Turkish |
| 硬件要求 | None currently, unless you'd like to download Jupyter Notebooks locally for offline work. |
| 如何通过 | 通过所有计分作业以完成课程。 |
| 用户评分 |
- 视频: Orthogonalization
- 视频: Single number evaluation metric
- 视频: Satisficing and Optimizing metric
- 视频: Train/dev/test distributions
- 视频: Size of the dev and test sets
- 视频: When to change dev/test sets and metrics
- 视频: Why human-level performance?
- 视频: Avoidable bias
- 视频: Understanding human-level performance
- 视频: Surpassing human-level performance
- 视频: Improving your model performance
- Reading: Machine Learning flight simulator
- 视频: Andrej Karpathy interview
- 视频: Cleaning up incorrectly labeled data
- 视频: Build your first system quickly, then iterate
- 视频: Training and testing on different distributions
- 视频: Bias and Variance with mismatched data distributions
- 视频: Addressing data mismatch
- 视频: Transfer learning
- 视频: Multi-task learning
- 视频: What is end-to-end deep learning?
- 视频: Whether to use end-to-end deep learning
- 视频: Ruslan Salakhutdinov interview
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
| 购买课程 | |
|---|---|
| 访问课程材料 | 可用 |
| 访问评分的材料 | 可用 |
| 收到最终成绩 | 可用 |
| 获得可共享的课程证书 | 可用 |
Andrew Ng is magical
It's very practical in the practice. and can save a lot time when you solve the problem.I think it very meaningful to my project
Lots of useful tips and tricks in this course. I feel that the videos could have been a bit shorter, and it would have been nice to have some programming assignments. Overall the course was extremely useful, however.
Valuable information that is well-organized and clearly delivered. Would benefit from a larger number of shorter exercises each week to cement learning after each group of lectures.