このコースについて： 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.
受講対象者： 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.
講師： Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
講師： Head Teaching Assistant - Kian Katanforoosh, Adjunct Lecturer at Stanford University, deeplearning.ai, Ecole Centrale Paris
講師： Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| 基本情報 | Deep Learning Specialization における 5 の 2 コース |
| レベル | Beginner |
| 所要時間 | 3 weeks, 3-6 hours per week |
| 言語 | English, 字幕： Chinese (Traditional), Chinese (Simplified) |
| 合格するには | すべての採点課題に合格すると、このコースを完了できます。 |
| ユーザーの評価 |
- 動画: Bias / Variance
- 動画: Basic Recipe for Machine Learning
- 動画: Regularization
- 動画: Why regularization reduces overfitting?
- 動画: Dropout Regularization
- 動画: Understanding Dropout
- 動画: Other regularization methods
- 動画: Normalizing inputs
- 動画: Vanishing / Exploding gradients
- 動画: Weight Initialization for Deep Networks
- 動画: Numerical approximation of gradients
- 動画: Gradient checking
- 動画: Gradient Checking Implementation Notes
- Notebook: Initialization
- Notebook: Regularization
- Notebook: Gradient Checking
- 動画: Yoshua Bengio interview
- 動画: Understanding mini-batch gradient descent
- 動画: Exponentially weighted averages
- 動画: Understanding exponentially weighted averages
- 動画: Bias correction in exponentially weighted averages
- 動画: Gradient descent with momentum
- 動画: RMSprop
- 動画: Adam optimization algorithm
- 動画: Learning rate decay
- 動画: The problem of local optima
- Notebook: Optimization
- 動画: Yuanqing Lin interview
- 動画: Using an appropriate scale to pick hyperparameters
- 動画: Hyperparameters tuning in practice: Pandas vs. Caviar
- 動画: Normalizing activations in a network
- 動画: Fitting Batch Norm into a neural network
- 動画: Why does Batch Norm work?
- 動画: Batch Norm at test time
- 動画: Softmax Regression
- 動画: Training a softmax classifier
- 動画: Deep learning frameworks
- 動画: 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.
| コースを購入 | |
|---|---|
| コースの教材へのアクセス | 利用可能 |
| 採点教材へのアクセス | 利用可能 |
| 最終成績の受領 | 利用可能 |
| 共有できるコースの修了証を取得 | 利用可能 |
Learning so much about how to optimize neural networks!
Add more theory
very good
Thanks Andrew and your team for teaching DNN to me. Then I will keep moving forward in AI industry based on your guiding afterward and aggressively build up personal AI research ability after courses.
Gary