Files

01_Introduction
02_TensorFlow_Way
03_Linear_Regression
04_Support_Vector_Machines
05_Nearest_Neighbor_Methods
06_Neural_Networks
07_Natural_Language_Processing
08_Convolutional_Neural_Networks
09_Recurrent_Neural_Networks
- 01_Introduction
- 02_Implementing_RNN_for_Spam_Prediction
- 03_Implementing_LSTM
- 04_Stacking_Multiple_LSTM_Layers
- 05_Creating_A_Sequence_To_Sequence_Model
- 06_Training_A_Siamese_Similarity_Measure
- images
- readme.md
10_Taking_TensorFlow_to_Production
11_More_with_TensorFlow
images
.gitignore
.travis.yml
LICENSE
circle.yml
readme.md
requirements.txt
test_script.py

09_Recurrent_Neural_Networks

Updated RNN Seq2seq for TFv.1.1

Apr 17, 2017

2d36c9e · Apr 17, 2017

This branch is 75 commits behind nfmcclure/tensorflow_cookbook:master.

Name		Name	Last commit message	Last commit date
parent directory ..
01_Introduction		01_Introduction	Updated git repo	Jan 28, 2017
02_Implementing_RNN_for_Spam_Prediction		02_Implementing_RNN_for_Spam_Prediction	BasicRNNCell is from tensorflow.contrib.rnn.	Mar 30, 2017
03_Implementing_LSTM		03_Implementing_LSTM	because TF1.0.1 changed stuff	Mar 13, 2017
04_Stacking_Multiple_LSTM_Layers		04_Stacking_Multiple_LSTM_Layers	fix variable scope error for Stack LSTM	Apr 1, 2017
05_Creating_A_Sequence_To_Sequence_Model		05_Creating_A_Sequence_To_Sequence_Model	Updated RNN Seq2seq for TFv.1.1	Apr 17, 2017
06_Training_A_Siamese_Similarity_Measure		06_Training_A_Siamese_Similarity_Measure	1.fix BasicRNN import error for production train.	Apr 7, 2017
images		images	added image	Mar 22, 2017
readme.md		readme.md	Links pointing to readme's header	Feb 8, 2017

readme.md

Ch 9: Recurrent Neural Networks

Introduction

We introduce Recurrent Neural Networks and how they are able to feed in a sequence and predict either a fixed target (categorical/numerical) or another sequence (sequence to sequence).

Implementing an RNN Model for Spam Prediction

We create an RNN model to improve on our spam/ham SMS text predictions.

Implementing an LSTM Model for Text Generation

We show how to implement a LSTM (Long Short Term Memory) RNN for Shakespeare language generation. (Word level vocabulary)

Stacking Multiple LSTM Layers

We stack multiple LSTM layers to improve on our Shakespeare language generation. (Character level vocabulary)

Creating a Sequence to Sequence Translation Model (Seq2Seq)

We show how to use TensorFlow's sequence-to-sequence models to train an English-German translation model.

Training a Siamese Similarity Measure

Here, we implement a Siamese RNN to predict the similarity of addresses and use it for record matching. Using RNNs for record matching is very versatile, as we do not have a fixed set of target categories and can use the trained model to predict similarities across new addresses.