关于此课程： This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: - Understand industry best-practices for building deep learning applications. - Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking, - Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. - Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance - Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization.
此课程适用人群： This class is for: - Learners that took the first course of the specialization: "Neural Networks and Deep Learning" - Anyone that already understands fully-connected neural networks, and wants to learn the practical aspects of making them work well.
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 2（共 5 门，Deep Learning Specialization ） |
| 级别 | 初级 |
| 承诺学习时间 | 3 weeks, 3-6 hours per week |
| 语言 | English, 字幕： Chinese (Traditional), Chinese (Simplified), Korean, Turkish |
| 如何通过 | 通过所有计分作业以完成课程。 |
| 用户评分 |
- 视频: Bias / Variance
- 视频: Basic Recipe for Machine Learning
- 视频: Regularization
- 视频: Why regularization reduces overfitting?
- 视频: Dropout Regularization
- 视频: Understanding Dropout
- 视频: Other regularization methods
- 视频: Normalizing inputs
- 视频: Vanishing / Exploding gradients
- 视频: Weight Initialization for Deep Networks
- 视频: Numerical approximation of gradients
- 视频: Gradient checking
- 视频: Gradient Checking Implementation Notes
- Notebook: Initialization
- Notebook: Regularization
- Notebook: Gradient Checking
- 视频: Yoshua Bengio interview
- 视频: Understanding mini-batch gradient descent
- 视频: Exponentially weighted averages
- 视频: Understanding exponentially weighted averages
- 视频: Bias correction in exponentially weighted averages
- 视频: Gradient descent with momentum
- 视频: RMSprop
- 视频: Adam optimization algorithm
- 视频: Learning rate decay
- 视频: The problem of local optima
- Notebook: Optimization
- 视频: Yuanqing Lin interview
- 视频: Using an appropriate scale to pick hyperparameters
- 视频: Hyperparameters tuning in practice: Pandas vs. Caviar
- 视频: Normalizing activations in a network
- 视频: Fitting Batch Norm into a neural network
- 视频: Why does Batch Norm work?
- 视频: Batch Norm at test time
- 视频: Softmax Regression
- 视频: Training a softmax classifier
- 视频: Deep learning frameworks
- 视频: TensorFlow
- Notebook: Tensorflow
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 |
A great introduction into Deep Learning with TensorFlow!
The cours would be even better, however, if the typos and faults reported in the discussion forum would be corrected in the course material as well :)
very helpful for tuning our model
my first output using tensorflow!amazing!!!
DA
Excellent information on improving networks. Real ground up understanding very helpful.