Transfer learning

Je zag dat je bij het trainen van een embeddinglaag veel parameters moet leren.

In deze oefening ga je zien dat je met transfer learning de voorgetrainde gewichten kunt gebruiken en ze niet hoeft bij te werken. Dat betekent dat alle parameters van de embeddinglaag vaststaan, en dat het model alleen de parameters van de andere lagen hoeft te leren.

De functie load_glove is al in de omgeving geladen en haalt de GloVe-matrix op als een numpy.ndarray-vector. Deze gebruikt de functie uit de dia's van de les om de GloVe-vectoren met 200 embedding-dimensies op te halen voor de vocabulaire die in deze oefening voorkomt.

Deze oefening maakt deel uit van de cursus

Recurrent Neural Networks (RNN's) voor taalmodellen met Keras

Cursus bekijken

Oefeninstructies

Gebruik de voorgedefinieerde functie om de GloVe-vectoren te laden.
Gebruik de initializer Constant op de voorgetrainde vectoren.
Voeg de outputlaag toe als een Dense met één unit.
Print de summary en controleer de trainable parameters.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Load the glove pre-trained vectors
glove_matrix = ____('glove_200d.zip')

# Create a model with embeddings
model = Sequential(name="emb_model")
model.add(Embedding(input_dim=vocabulary_size + 1, output_dim=wordvec_dim, 
                    embeddings_initializer=____(glove_matrix), 
                    input_length=sentence_len, trainable=False))
model.add(GRU(128))
model.add(____)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Print the summaries of the model with embeddings
model.____

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Recurrent Neural Networks (RNN's) voor taalmodellen met Keras

SkillTag.level.advancedSkillTag.label

4.8+

Begin de cursus gratis

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.

Exercise 1: Introduction to the course Exercise 2: Comparing the number of parameter of RNN and ANN Exercise 3: Sentiment analysis Exercise 4: Sequence to sequence models Exercise 5: Introduction to language models Exercise 6: Getting used to text data Exercise 7: Preparing text data for model input Exercise 8: Transforming new text Exercise 9: Introduction to RNN inside Keras Exercise 10: Keras models Exercise 11: Keras preprocessing Exercise 12: Your first RNN model

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.

Exercise 1: Ver verdwijnende en exploderende gradiënten Exercise 2: Exploding gradient-probleem Exercise 3: Vanishing gradient-probleem Exercise 4: GRU- en LSTM-cellen Exercise 5: GRU-cellen zijn beter dan SimpleRNN Exercise 6: RNN-lagen stapelen Exercise 7: De Embedding-laag Exercise 8: Vergelijking van het aantal parameters Exercise 9: Transfer learning

Huidige oefening

Exercise 10: Embeddings verbeteren de prestaties Exercise 11: Sentimentclassificatie herbekeken Exercise 12: Betere sentimentclassificatie Exercise 13: De CNN-laag gebruiken

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.

Exercise 1: Data pre-processing Exercise 2: Prepare label vectors Exercise 3: Pre-process data Exercise 4: Transfer learning for language models Exercise 5: Transfer learning starting point Exercise 6: Word2Vec Exercise 7: Multi-class classification models Exercise 8: Exploring 20 News Groups dataset Exercise 9: Classifying news articles Exercise 10: Assessing the model's performance Exercise 11: Precision-Recall trade-off Exercise 12: Precision or Recall, that is the question Exercise 13: Performance on multi-class classification

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.

Exercise 1: Sequence to Sequence Models Exercise 2: Text generation examples Exercise 3: NMT example Exercise 4: The Text Generating Function Exercise 5: Predict next character Exercise 6: Generate sentence with context Exercise 7: Change the probability scale Exercise 8: Text Generation Models Exercise 9: Create vectors of sentences and next characters Exercise 10: Preparing the data for training Exercise 11: Creating the text generation model Exercise 12: Neural Machine Translation Exercise 13: Preparing the input text Exercise 14: Preparing the output text Exercise 15: Translate Portuguese to English Exercise 16: Congratulations!