Loved by learners at thousands of companies
Deep learning is here to stay! It's the go-to technique to solve complex problems that arise with unstructured data and an incredible tool for innovation. Keras is one of the frameworks that make it easier to start developing deep learning models, and it's versatile enough to build industry-ready models in no time. In this course, you will learn regression and save the earth by predicting asteroid trajectories, apply binary classification to distinguish between real and fake dollar bills, use multiclass classification to decide who threw which dart at a dart board, learn to use neural networks to reconstruct noisy images and much more. Additionally, you will learn how to better control your models during training and how to tune them to boost their performance.
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!
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.Binary classification50 xpExploring dollar bills100 xpA binary classification model100 xpIs this dollar bill fake ?100 xpMulti-class classification50 xpA multi-class model100 xpPrepare your dataset100 xpTraining on dart throwers100 xpSoftmax predictions100 xpMulti-label classification50 xpAn irrigation machine100 xpTraining with multiple labels100 xpKeras callbacks50 xpThe history callback100 xpEarly stopping your model100 xpA combination of callbacks100 xp
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.Learning curves50 xpLearning the digits100 xpIs the model overfitting?100 xpDo we need more data?100 xpActivation functions50 xpDifferent activation functions50 xpComparing activation functions100 xpComparing activation functions II100 xpBatch size and batch normalization50 xpChanging batch sizes100 xpBatch normalizing a familiar model100 xpBatch normalization effects100 xpHyperparameter tuning50 xpPreparing a model for tuning100 xpTuning the model parameters100 xpTraining with cross-validation100 xp
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.Tensors, layers, and autoencoders50 xpIt's a flow of tensors100 xpNeural separation100 xpBuilding an autoencoder100 xpDe-noising like an autoencoder100 xpIntro to CNNs50 xpBuilding a CNN model100 xpLooking at convolutions100 xpPreparing your input image100 xpUsing a real world model100 xpIntro to LSTMs50 xpText prediction with LSTMs100 xpBuild your LSTM model100 xpDecode your predictions100 xpTest your model!50 xpYou're done!50 xp
PrerequisitesMachine Learning with scikit-learn
Data Scientist & Founder
Miguel is an entrepreneur and data scientist. He has worked at companies like Endesa, where he applied Deep Learning to solve and automate problems related to electrical consumption curves. He is currently one of the founders at XtremeAI, where he is working in building products delivering automatic data extraction from complex documents. In it's free time he plays music, takes pictures, experiments with AI and thinks about the next big idea to built. You can follow or contact him on Twitter and LinkedIn.
What do other learners have to say?
I've used other sites—Coursera, Udacity, things like that—but DataCamp's been the one that I've stuck with.
Devon Edwards Joseph
Lloyds Banking Group
DataCamp is the top resource I recommend for learning data science.
Harvard Business School
DataCamp is by far my favorite website to learn from.
Decision Science Analytics, USAA