Acerca de este curso: 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.
Para quién es esta clase: 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.
Enseñado por: Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
Enseñado por: Head Teaching Assistant - Kian Katanforoosh, Adjunct Lecturer at Stanford University, deeplearning.ai, Ecole Centrale Paris
Enseñado por: Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| Información básica | Curso 2 de 5 en Deep Learning Specialization |
| Nivel | Beginner |
| Compromiso | 3 weeks, 3-6 hours per week |
| Idioma | English, Subtítulos: Chinese (Traditional), Chinese (Simplified) |
| Cómo aprobar | Aprueba todas las tareas calificadas para completar el curso. |
| Calificaciones del usuario |
- Vídeo: Train / Dev / Test sets
- Vídeo: Bias / Variance
- Vídeo: Basic Recipe for Machine Learning
- Vídeo: Regularization
- Vídeo: Why regularization reduces overfitting?
- Vídeo: Dropout Regularization
- Vídeo: Understanding Dropout
- Vídeo: Other regularization methods
- Vídeo: Normalizing inputs
- Vídeo: Vanishing / Exploding gradients
- Vídeo: Weight Initialization for Deep Networks
- Vídeo: Numerical approximation of gradients
- Vídeo: Gradient checking
- Vídeo: Gradient Checking Implementation Notes
- 노트: Initialization
- 노트: Regularization
- 노트: Gradient Checking
- Vídeo: Yoshua Bengio interview
- Vídeo: Mini-batch gradient descent
- Vídeo: Understanding mini-batch gradient descent
- Vídeo: Exponentially weighted averages
- Vídeo: Understanding exponentially weighted averages
- Vídeo: Bias correction in exponentially weighted averages
- Vídeo: Gradient descent with momentum
- Vídeo: RMSprop
- Vídeo: Adam optimization algorithm
- Vídeo: Learning rate decay
- Vídeo: The problem of local optima
- 노트: Optimization
- Vídeo: Yuanqing Lin interview
- Vídeo: Tuning process
- Vídeo: Using an appropriate scale to pick hyperparameters
- Vídeo: Hyperparameters tuning in practice: Pandas vs. Caviar
- Vídeo: Normalizing activations in a network
- Vídeo: Fitting Batch Norm into a neural network
- Vídeo: Why does Batch Norm work?
- Vídeo: Batch Norm at test time
- Vídeo: Softmax Regression
- Vídeo: Training a softmax classifier
- Vídeo: Deep learning frameworks
- Vídeo: TensorFlow
- 노트: Tensorflow
각 강좌는 대화형 교과서 형식으로 이루어지며, 사전 녹화된 비디오, 테스트, 프로젝트를 포함합니다.
수천 명의 다른 동료 학습자와 함께 논의하고, 강좌 자료에 대하여 토론하고, 개념 습득을 위해 서로 도움을 받으십시오.
귀하의 성과를 공식적으로 인정받아 친구, 동료, 회사에 성과를 공유해 보세요.
| Comprar curso | |
|---|---|
| Accede a los materiales del curso | Disponible |
| Accede a los materiales con calificación | Disponible |
| Recibe una calificación final | Disponible |
| Obtén un Certificado de curso para compartir | Disponible |
最后程序注释中有少量错误，别的很好
great course
Well organized and clearly explained. I finally understand tensorflow.
Found a lot of interesting details about NN that I did not know. This is a much better course than the first one. IncludesTensorflow exercises, which is useful. Nevertheless, proofs are still omitted for some results like initializations. It is not hard to google, but I bet lecturers could explain them much faster than diving into science literature. Otherwise, intuitional explanations of Adam using exponential smoothing, or physics analogy of momentum are just brilliant.