Loved by learners at thousands of companies
Machine Learning models are based on numerical values to make predictions/classification, but how can computers deal with text data? With the huge increase of available text data, applications such as automatic document classification, text generation, and neural machine translation became possible. In this course, you will learn how to use Recurrent Neural Networks to classify text (binary and multiclass), generate phrases simulating the character Sheldon from The Big Bang Theory TV Show, and translate Portuguese sentences into English. Are you ready to start your journey into Language Models using Keras and Python? Dive in!
Recurrent Neural Networks and KerasFree
In this chapter, you will learn the foundations of Recurrent Neural Networks (RNN). Starting with some prerequisites, continuing to understanding how information flows through the network and finally seeing how to implement such models with Keras in the sentiment classification task.Introduction to the course50 xpKeras models: Sequential50 xpKeras models: Model50 xpComparing the number of parameter of RNN and ANN50 xpSentiment analysis100 xpSequence to sequence models50 xpIntroduction to language models50 xpGetting used to text data100 xpPreparing text data for model input100 xpTransforming new text100 xpIntroduction to RNN inside Keras50 xpKeras models100 xpKeras preprocessing100 xpYour first RNN model100 xp
You will learn about the vanishing and exploding gradient problems, often occurring in RNNs, and how to deal with them with the GRU and LSTM cells. Furthermore, you'll create embedding layers for language models and revisit the sentiment classification task.Vanishing and exploding gradients50 xpExploding gradient problem100 xpVanishing gradient problem100 xpGRU and LSTM cells50 xpGRU cells are better than simpleRNN100 xpStacking RNN layers100 xpThe Embedding layer50 xpNumber of parameters comparison100 xpTransfer learning100 xpEmbeddings improves performance100 xpSentiment classification revisited50 xpBetter sentiment classification100 xpUsing the CNN layer100 xp
Next, in this chapter you will learn how to prepare data for the multi-class classification task, as well as the differences between multi-class classification and binary classification (sentiment analysis). Finally, you will learn how to create models and measure their performance with Keras.Data pre-processing50 xpPrepare label vectors100 xpPre-process data100 xpTransfer learning for language models50 xpTransfer learning starting point100 xpWord2Vec100 xpMulti-class classification models50 xpExploring 20 News Groups dataset100 xpClassifying news articles100 xpAssessing the model's performance50 xpPrecision-Recall trade-off100 xpPrecision or Recall, that is the question100 xpPerformance on multi-class classification100 xp
Sequence to Sequence Models
This chapter introduces you to two applications of RNN models: Text Generation and Neural Machine Translation. You will learn how to prepare the text data to the format needed by the models. The Text Generation model is used for replicating a character's way of speech and will have some fun mimicking Sheldon from The Big Bang Theory. Neural Machine Translation is used for example by Google Translate in a much more complex model. In this chapter, you will create a model that translates Portuguese small phrases into English.Sequence to Sequence Models50 xpText generation examples100 xpNMT example100 xpThe Text Generating Function50 xpPredict next character100 xpGenerate sentence with context100 xpChange the probability scale100 xpText Generation Models50 xpCreate vectors of sentences and next characters100 xpPreparing the data for training100 xpCreating the text generation model100 xpNeural Machine Translation50 xpPreparing the input text100 xpPreparing the output text100 xpTranslate Portuguese to English100 xpCongratulations!50 xp
In the following tracksDeep Learning for NLP
DatasetsScripts of the TV show The Big Bang Theory.Sample of small sentences in English and Portuguese
I am a Data Scientist focusing my work and research on using machine learning on text data. I entered the field when I co-founded a startup company in the field of RegTech that automatically collect, classify and distribute regulations on highly regulated markets, and am currently a Ph.D. student at Tsinghua-Berkeley Shenzhen Institute, a partner program from Tsinghua University from China and UC Berkeley from the USA.
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