Course
Introduction to Deep Learning with Keras
IntermediateSkill Level
Updated 09/2022PythonArtificial Intelligence4 hr15 videos59 Exercises4,950 XP45,519Statement of Accomplishment
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.Loved by learners at thousands of companies
Training 2 or more people?
Try DataCamp for BusinessCourse Description
Prerequisites
Supervised Learning with scikit-learn1
Introducing Keras
In this first chapter, you will get introduced to neural networks, understand what kind of problems they can solve, and when to use them. You will also build several networks and save the earth by training a regression model that approximates the orbit of a meteor that is approaching us!
2
Going Deeper
By the end of this chapter, you will know how to solve binary, multi-class, and multi-label problems with neural networks. All of this by solving problems like detecting fake dollar bills, deciding who threw which dart at a board, and building an intelligent system to water your farm. You will also be able to plot model training metrics and to stop training and save your models when they no longer improve.
3
Improving Your Model Performance
In the previous chapters, you've trained a lot of models! You will now learn how to interpret learning curves to understand your models as they train. You will also visualize the effects of activation functions, batch-sizes, and batch-normalization. Finally, you will learn how to perform automatic hyperparameter optimization to your Keras models using sklearn.
4
Advanced Model Architectures
It's time to get introduced to more advanced architectures! You will create an autoencoder to reconstruct noisy images, visualize convolutional neural network activations, use deep pre-trained models to classify images and learn more about recurrent neural networks and working with text as you build a network that predicts the next word in a sentence.
Introduction to Deep Learning with Keras
Course Complete
Earn Statement of Accomplishment
Add this credential to your LinkedIn profile, resume, or CVShare it on social media and in your performance reviewEnroll Now
FAQs
What prior machine learning experience do I need for this Keras course?
You should have completed Supervised Learning with scikit-learn, Introduction to Statistics in Python, and pandas fundamentals. The course assumes comfort with classification and regression concepts.
What kinds of neural network tasks will I work on?
You will predict asteroid trajectories with regression, classify real versus fake dollar bills, perform multiclass dart board classification, and reconstruct noisy images with autoencoders.
Does the course cover hyperparameter tuning for Keras models?
Yes. Chapter 3 teaches you to visualize the effects of activation functions, batch sizes, and batch normalization, then perform automatic hyperparameter optimization using sklearn.
What advanced architectures are introduced?
The final chapter covers autoencoders for image reconstruction, convolutional neural networks for image classification, deep pre-trained models, and recurrent neural networks for text prediction.
Will I learn how to monitor model training and prevent overfitting?
Yes. You will learn to plot training metrics, interpret learning curves, use early stopping to halt training when performance plateaus, and save your best models during the process.
Join over 19 million learners and start Introduction to Deep Learning with Keras today!
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.Grow your data skills with DataCamp for Mobile
Make progress on the go with our mobile courses and daily 5-minute coding challenges.