Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

Product type
Logo Coursera (CC)
Provider rating: starstarstarstar_halfstar_border 7.2 Coursera (CC) has an average rating of 7.2 (out of 6 reviews)

Need more information? Get more details on the site of the provider.

Description

When you enroll for courses through Coursera you get to choose for a paid plan or for a free plan

  • Free plan: No certicification and/or audit only. You will have access to all course materials except graded items.
  • Paid plan: Commit to earning a Certificate—it's a trusted, shareable way to showcase your new skills.

About this course: 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 …

Read the complete description

Frequently asked questions

There are no frequently asked questions yet. If you have any more questions or need help, contact our customer service.

Didn't find what you were looking for? See also: Neural Networks, Blog Writing, WordPress, Business Writing, and Writing for the web.

When you enroll for courses through Coursera you get to choose for a paid plan or for a free plan

  • Free plan: No certicification and/or audit only. You will have access to all course materials except graded items.
  • Paid plan: Commit to earning a Certificate—it's a trusted, shareable way to showcase your new skills.

About this course: 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.

Who is this class for: 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.

Created by:  deeplearning.ai
  • Taught by:  Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain

Basic Info Course 2 of 5 in the Deep Learning Specialization Level Beginner Commitment 3 weeks, 3-6 hours per week Language English How To Pass Pass all graded assignments to complete the course. User Ratings 4.9 stars Average User Rating 4.9See what learners said Trabajo del curso

Cada curso es como un libro de texto interactivo, con videos pregrabados, cuestionarios y proyectos.

Ayuda de tus compañeros

Conéctate con miles de estudiantes y debate ideas y materiales del curso, y obtén ayuda para dominar los conceptos.

Certificados

Obtén reconocimiento oficial por tu trabajo y comparte tu éxito con amigos, compañeros y empleadores.

deeplearning.ai deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders.

Syllabus


WEEK 1


Practical aspects of Deep Learning



15 videos expand


  1. Video: Train / Dev / Test sets
  2. Video: Bias / Variance
  3. Video: Basic Recipe for Machine Learning
  4. Video: Regularization
  5. Video: Why regularization reduces overfitting?
  6. Video: Dropout Regularization
  7. Video: Understanding Dropout
  8. Video: Other regularization methods
  9. Video: Normalizing inputs
  10. Video: Vanishing / Exploding gradients
  11. Video: Weight Initialization for Deep Networks
  12. Video: Numerical approximation of gradients
  13. Video: Gradient checking
  14. Video: Gradient Checking Implementation Notes
  15. Libreta: Initialization
  16. Libreta: Regularization
  17. Libreta: Gradient Checking
  18. Video: Yoshua Bengio interview

Graded: Practical aspects of deep learning
Graded: Initialization
Graded: Regularization
Graded: Gradient Checking

WEEK 2


Optimization algorithms



11 videos expand


  1. Video: Mini-batch gradient descent
  2. Video: Understanding mini-batch gradient descent
  3. Video: Exponentially weighted averages
  4. Video: Understanding exponentially weighted averages
  5. Video: Bias correction in exponentially weighted averages
  6. Video: Gradient descent with momentum
  7. Video: RMSprop
  8. Video: Adam optimization algorithm
  9. Video: Learning rate decay
  10. Video: The problem of local optima
  11. Libreta: Optimization
  12. Video: Yuanqing Lin interview

Graded: Optimization algorithms
Graded: Optimization

WEEK 3


Hyperparameter tuning, Batch Normalization and Programming Frameworks



11 videos expand


  1. Video: Tuning process
  2. Video: Using an appropriate scale to pick hyperparameters
  3. Video: Hyperparameters tuning in practice: Pandas vs. Caviar
  4. Video: Normalizing activations in a network
  5. Video: Fitting Batch Norm into a neural network
  6. Video: Why does Batch Norm work?
  7. Video: Batch Norm at test time
  8. Video: Softmax Regression
  9. Video: Training a softmax classifier
  10. Video: Deep learning frameworks
  11. Video: TensorFlow
  12. Libreta: Tensorflow

Graded: Hyperparameter tuning, Batch Normalization, Programming Frameworks
Graded: Tensorflow
There are no reviews yet.

Share your review

Do you have experience with this course? Submit your review and help other people make the right choice. As a thank you for your effort we will donate $1.- to Stichting Edukans.

There are no frequently asked questions yet. If you have any more questions or need help, contact our customer service.