Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Institution Logo

Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

deeplearning.ai and Stanford University via Coursera

Overview

In the second course of the Deep Learning Specialization, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically.

By the end, you will learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications; be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking; implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence; and implement a neural network in TensorFlow.

The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI.

Syllabus

  • Practical aspects of Deep Learning
  • Optimization algorithms
  • Hyperparameter tuning, Batch Normalization and Programming Frameworks

Taught by

Andrew Ng

Related Courses

Reviews

5.0 rating, based on 3 reviews

Start your review of Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

  • Nattapon Sub-Anake completed this course, spending 6 hours a week on it and found the course difficulty to be medium.

    I finished this second deep learning course and I like it very much. I am looking forward for more courses in this deep learning series. Andrew is doing a great job here.
  • Silveira Homero completed this course, spending 9 hours a week on it and found the course difficulty to be medium.

    This is a follow up course to Neural Networks and Deep Learning so you must start with the latter. The practical side of the teaching was very interesting.
  • Profile image for Raivis Joksts
    Raivis Joksts

    Raivis Joksts completed this course, spending 6 hours a week on it and found the course difficulty to be easy.

    A good look at most important parameters that impact DL models. Again it is math heavy, but it' s ok to just understand basic logic behind it. Has some TensorFlow practical tasks, which are easy to complete, but you may wish to read up on TF on your own to understand how it works in general, especially if you have used other DLK framework before - like PyTorch, for example.

Never stop learning Never Stop Learning!

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free