Об этом курсе: 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.
Для кого этот курс: 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.
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 2 of 5 in the Deep Learning Specialization |
| Уровень | Начинающий |
| Выполнение | 3 weeks, 3-6 hours per week |
| Язык | English, Субтитры: Korean, Chinese (Traditional), Chinese (Simplified) |
| Как пройти курс | Чтобы пройти курс, выполните все оцениваемые задания. |
| Оценки пользователей |
- Видео: Bias / Variance
- Видео: Basic Recipe for Machine Learning
- Видео: Regularization
- Видео: Why regularization reduces overfitting?
- Видео: Dropout Regularization
- Видео: Understanding Dropout
- Видео: Other regularization methods
- Видео: Normalizing inputs
- Видео: Vanishing / Exploding gradients
- Видео: Weight Initialization for Deep Networks
- Видео: Numerical approximation of gradients
- Видео: Gradient checking
- Видео: Gradient Checking Implementation Notes
- Bloc-notes: Initialization
- Bloc-notes: Regularization
- Bloc-notes: Gradient Checking
- Видео: Yoshua Bengio interview
- Видео: Understanding mini-batch gradient descent
- Видео: Exponentially weighted averages
- Видео: Understanding exponentially weighted averages
- Видео: Bias correction in exponentially weighted averages
- Видео: Gradient descent with momentum
- Видео: RMSprop
- Видео: Adam optimization algorithm
- Видео: Learning rate decay
- Видео: The problem of local optima
- Bloc-notes: Optimization
- Видео: Yuanqing Lin interview
- Видео: Using an appropriate scale to pick hyperparameters
- Видео: Hyperparameters tuning in practice: Pandas vs. Caviar
- Видео: Normalizing activations in a network
- Видео: Fitting Batch Norm into a neural network
- Видео: Why does Batch Norm work?
- Видео: Batch Norm at test time
- Видео: Softmax Regression
- Видео: Training a softmax classifier
- Видео: Deep learning frameworks
- Видео: TensorFlow
- Bloc-notes: Tensorflow
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.
| 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 |
very good content
Very useful follow up to the first course in this specialization. Learned all the details of how to tune and optimize a deep neural network, as well as nice introduction to Tensorflow. Some typos in the comments of the final assignments but they were easy to spot. This time Jupiter notebooks worked better that during the time I was working on the previous course with less or no resets required.
Great!
P
기본의 코스를 Numpy를 통해서 배우다, 본격적으로 프레임 워크 (Tensorflow) 들어가니 이해가 잘 됩니다. 특히 머신 러닝 강좌를 이렇게 코딩을 섞어서 만들기까지, 얼마나 많은 정성과 노력이 들어갔음을 알기에 경의를 표합니다.