關於此課程：If you want to break into cutting-edge AI, this course will help you do so. Deep learning engineers are highly sought after, and mastering deep learning will give you numerous new career opportunities. Deep learning is also a new "superpower" that will let you build AI systems that just weren't possible a few years ago. In this course, you will learn the foundations of deep learning. When you finish this class, you will: - Understand the major technology trends driving Deep Learning - Be able to build, train and apply fully connected deep neural networks - Know how to implement efficient (vectorized) neural networks - Understand the key parameters in a neural network's architecture This course also teaches you how Deep Learning actually works, rather than presenting only a cursory or surface-level description. So after completing it, you will be able to apply deep learning to a your own applications. If you are looking for a job in AI, after this course you will also be able to answer basic interview questions. This is the first course of the Deep Learning Specialization.
此課程適用人群：Prerequisites: Expected: - Programming: Basic Python programming skills, with the capability to work effectively with data structures. Recommended: - Mathematics: Matrix vector operations and notation. - Machine Learning: Understanding how to frame a machine learning problem, including how data is represented will be beneficial. If you have taken my Machine Learning Course here, you have much more than the needed level of knowledge.
教學方： Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
教學方： Head Teaching Assistant - Kian Katanforoosh, Lecturer of Computer Science at Stanford University, deeplearning.ai, Ecole CentraleSupelec
教學方： Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| 基本信息 | 課程 1（共 5 門，Deep Learning Specialization ） |
| 級別 | 中級 |
| 承諾學習時間 | 4 weeks of study, 3-6 hours a week |
| 語言 | English, 字幕：Chinese (Traditional), Chinese (Simplified), Portuguese (Brazilian), Korean, Turkish, Japanese |
| 如何通過 | 通過所有計分作業以完成課程。 |
| 用戶評分 |
- 視頻: What is a neural network?
- 視頻: Supervised Learning with Neural Networks
- 視頻: Why is Deep Learning taking off?
- 視頻: About this Course
- Lecture: Frequently Asked Questions
- 視頻: Course Resources
- Lecture: How to use Discussion Forums
- 視頻: Geoffrey Hinton interview
- 視頻: Logistic Regression
- 視頻: Logistic Regression Cost Function
- 視頻: Gradient Descent
- 視頻: Derivatives
- 視頻: More Derivative Examples
- 視頻: Computation graph
- 視頻: Derivatives with a Computation Graph
- 視頻: Logistic Regression Gradient Descent
- 視頻: Gradient Descent on m Examples
- 視頻: Vectorization
- 視頻: More Vectorization Examples
- 視頻: Vectorizing Logistic Regression
- 視頻: Vectorizing Logistic Regression's Gradient Output
- 視頻: Broadcasting in Python
- 視頻: A note on python/numpy vectors
- 視頻: Quick tour of Jupyter/iPython Notebooks
- 視頻: Explanation of logistic regression cost function (optional)
- Lecture: Deep Learning Honor Code
- Lecture: Programming Assignment FAQ
- Bloc-notes: Python Basics with numpy (optional)
- Programmation non notée: Python Basics with numpy (optional)
- Bloc-notes: Logistic Regression with a Neural Network mindset
- 視頻: Pieter Abbeel interview
- 視頻: Neural Network Representation
- 視頻: Computing a Neural Network's Output
- 視頻: Vectorizing across multiple examples
- 視頻: Explanation for Vectorized Implementation
- 視頻: Activation functions
- 視頻: Why do you need non-linear activation functions?
- 視頻: Derivatives of activation functions
- 視頻: Gradient descent for Neural Networks
- 視頻: Backpropagation intuition (optional)
- 視頻: Random Initialization
- Bloc-notes: Planar data classification with a hidden layer
- 視頻: Ian Goodfellow interview
- 視頻: Forward Propagation in a Deep Network
- 視頻: Getting your matrix dimensions right
- 視頻: Why deep representations?
- 視頻: Building blocks of deep neural networks
- 視頻: Forward and Backward Propagation
- 視頻: Parameters vs Hyperparameters
- 視頻: What does this have to do with the brain?
- Bloc-notes: Building your Deep Neural Network: Step by Step
- Bloc-notes: Deep Neural Network - Application
Chaque cours fonctionne comme un manuel interactif en proposant des vidéos préenregistrées, des quiz et des projets.
Connectez-vous à des milliers d'autres étudiants et débattez sur des idées, discutez le contenu du cours et obtenez de l'aide pour en maîtriser les concepts.
Obtenez une reconnaissance officielle pour votre travail et partagez votre réussite avec vos amis, vos collègues et vos employeurs.
| 購買課程 | |
|---|---|
| 訪問課程材料 | 可用 |
| 訪問評分的材料 | 可用 |
| 收到最終成績 | 可用 |
| 獲得可共享的課程證書 | 可用 |
Exceptional Introduction to Deep Learning. 2 years after completing the Machine LEarning course from Andrew, it felt like catching up with an old friend. This is really amazing.
My only development comment would be that the exercise are a bit too guided.
This course was pretty good in giving me an initial understanding of what a neural network is, and what deep learning refers to. I found week #2 to be the most informative, with week #3 and week #4 being the second and least informative respectively. Week #1 was just an introduction so I didn't count it.
The programming exercises were a little like 'fill in the blank' type things, and could be completed just by looking at the examples and following the hints. I thought it was neat that I could build an image recognition program, but there are a lot of points in my understanding that just aren't filled in yet. However, like any complicated subject, you can't have a deep understanding after only a few hours of videos.
Overall, it was a fun first course for me. It was also my first Coursera course, so maybe completing some others will give me a better perspective.
Fantastic content, great delivery and good assignments.
ya
GOOD COURSE I RECOMMEND