Explore

Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

Approx. 22 hours to complete

Save Course

Go to Course

Course Summary

This course teaches you how to build deep neural networks and improve your deep learning skills. You will learn about convolutional networks, recurrent networks, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more.

Key Learning Points

Gain a deep understanding of deep neural networks and their applications
Learn how to build various types of neural networks from scratch
Improve your deep learning skills and stay up-to-date with the latest techniques

Job Positions & Salaries of people who have taken this course might have

- USA: $112,000
- India: ₹1,200,000
- Spain: €42,000
- USA: $112,000
- India: ₹1,200,000
- Spain: €42,000
- USA: $117,000
- India: ₹1,000,000
- Spain: €36,000
- USA: $112,000
- India: ₹1,200,000
- Spain: €42,000
- USA: $117,000
- India: ₹1,000,000
- Spain: €36,000
- USA: $138,000
- India: ₹2,400,000
- Spain: €56,000

Learning Outcomes

Build and train deep neural networks from scratch
Understand the inner workings of neural networks and how to optimize them
Apply deep learning techniques to real-world problems

Prerequisites or good to have knowledge before taking this course

Basic knowledge of Python programming
Familiarity with calculus and linear algebra

Course Difficulty Level

Intermediate

Course Format

Online self-paced course
Video lectures with quizzes and programming assignments

Similar Courses

Machine Learning
Neural Networks and Deep Learning
Applied Data Science with Python

Related Education Paths

Related Books

Description

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.

Outline

Practical Aspects of Deep Learning
Train / Dev / Test sets
Bias / Variance
Basic Recipe for Machine Learning
Regularization
Why Regularization Reduces Overfitting?
Dropout Regularization
Understanding Dropout
Other Regularization Methods
Normalizing Inputs
Vanishing / Exploding Gradients
Weight Initialization for Deep Networks
Numerical Approximation of Gradients
Gradient Checking
Gradient Checking Implementation Notes
Yoshua Bengio Interview
Connect with your Mentors and Fellow Learners on Discourse!
Clarification about Upcoming Regularization Video
Clarification about Upcoming Understanding Dropout Video
Lectures in PDF
How to Refresh your Workspace
Practical aspects of Deep Learning

Optimization Algorithms
Mini-batch Gradient Descent
Understanding Mini-batch Gradient Descent
Exponentially Weighted Averages
Understanding Exponentially Weighted Averages
Bias Correction in Exponentially Weighted Averages
Gradient Descent with Momentum
RMSprop
Adam Optimization Algorithm
Learning Rate Decay
The Problem of Local Optima
Yuanqing Lin Interview
Clarification about Upcoming Adam Optimization Video
Clarification about Learning Rate Decay Video
Lectures in PDF
Optimization Algorithms

Hyperparameter Tuning, Batch Normalization and Programming Frameworks
Tuning Process
Using an Appropriate Scale to pick Hyperparameters
Hyperparameters Tuning in Practice: Pandas vs. Caviar
Normalizing Activations in a Network
Fitting Batch Norm into a Neural Network
Why does Batch Norm work?
Batch Norm at Test Time
Softmax Regression
Training a Softmax Classifier
Deep Learning Frameworks
TensorFlow
Clarification about Upcoming Normalizing Activations in a Network Video
Clarifications about Upcoming Softmax Video
(Optional) Learn about Gradient Tape and More
Lectures in PDF
References
Acknowledgments
Hyperparameter tuning, Batch Normalization, Programming Frameworks

Summary of User Reviews

This course on deep neural networks is highly-rated among users for its comprehensive coverage of the subject matter and practical exercises. Many users especially appreciated the clear explanations and real-world examples provided throughout the course.

Key Aspect Users Liked About This Course

Clear explanations and real-world examples

Pros from User Reviews

Comprehensive coverage of deep neural networks
Practical exercises to reinforce learning
Clear explanations and real-world examples
Engaging and knowledgeable instructors
Great for beginners and intermediate learners

Cons from User Reviews

Some users found the course content too basic
Lack of advanced topics
No hands-on projects
Some technical issues with the platform
Limited interaction with instructors

Recommended for you