Patlayan gradyan problemi

Video egzersizinde, RNN modelleriyle çalışırken ortaya çıkabilecek iki sorunu öğrendin: sönümlenen ve patlayan gradyan problemleri.

Bu egzersiz, patlayan gradyan problemini inceliyor; bir fonksiyonun türevinin üstel olarak artabileceğini gösteriyor ve bunu basit bir teknikle nasıl çözeceğini anlatıyor.

Veriler çalışma ortamında zaten X_train, X_test, y_train ve y_test olarak yüklü.

Bir Stochastic Gradient Descent (SGD) iyileştirici (optimizer) ve kayıp fonksiyonu olarak Mean Squared Error (MSE) kullanacaksın.

İlk adımda, eğitim ve test kümelerinde MSE hesaplayarak gradyanın nasıl patladığını gözlemleyeceksin. 2. adımda ise clipvalue parametresini kullanarak iyileştiriciyi değiştirip sorunu çözeceksin.

Keras'ta Stochastic Gradient Descent SGD olarak yüklenir.

Bu egzersiz

Keras ile Dil Modellemesi için Yinelenen Sinir Ağları (RNN)

kursunun bir parçasıdır

Kursu Görüntüle

Uygulamalı interaktif egzersiz

Bu örnek kodu tamamlayarak bu egzersizi bitirin.

# Create a Keras model with one hidden Dense layer
model = Sequential()
model.add(Dense(25, input_dim=20, activation='relu', kernel_initializer=he_uniform(seed=42)))
model.add(Dense(1, activation='linear'))

# Compile and fit the model
model.compile(loss='mean_squared_error', optimizer=____(learning_rate=0.01, momentum=0.9))
history = model.fit(X_train, y_train, validation_data=(____, ____), epochs=100, verbose=0)

# See Mean Square Error for train and test data
train_mse = model.____(X_train, y_train, verbose=0)
test_mse = model.evaluate(X_test, y_test, verbose=0)

# Print the values of MSE
print('Train: %.3f, Test: %.3f' % (____, ____))

Kodu Düzenle ve Çalıştır

Bu egzersiz

Keras ile Dil Modellemesi için Yinelenen Sinir Ağları (RNN)

kursunun bir parçasıdır

AvançadoNível de habilidade

4.8+

Kursa Ücretsiz Başlayın

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: Kaybolan ve patlayan gradyanlar Exercise 2: Patlayan gradyan problemi

Geçerli Egzersiz

Exercise 3: Kaybolan gradyan sorunu Exercise 4: GRU ve LSTM hücreleri Exercise 5: GRU hücreleri simpleRNN'den daha iyidir Exercise 6: RNN katmanlarını istiflemek Exercise 7: Embedding katmanı Exercise 8: Parametre sayısı karşılaştırması Exercise 9: Transfer öğrenimi Exercise 10: Embedding'ler performansı artırır Exercise 11: Duygu sınıflandırmasına yeniden bakış Exercise 12: Daha iyi duygu sınıflandırması Exercise 13: CNN katmanını kullanma

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!