RNNs in Tensorflow, a Practical Guide and Undocumented Features

In a previous tutorial series I went over some of the theory behind Recurrent Neural Networks (RNNs) and the implementation of a simple RNN from scratch. That’s a useful exercise, but in practice we use libraries like Tensorflow with high-level primitives for dealing with RNNs.

With that using an RNN should be as easy as calling a function, right? Unfortunately that’s not quite the case. In this post I want to go over some of the best practices for working with RNNs in Tensorflow, especially the functionality that isn’t well documented on the official site.

The post comes with a Github repository that contains Jupyter notebooks with minimal examples for:

Deep Learning for Chatbots, Part 2 – Implementing a Retrieval-Based Model in Tensorflow

The Code and data for this tutorial is on Github.

Retrieval-Based bots

In this post we’ll implement a retrieval-based bot. Retrieval-based models have a repository of pre-defined responses they can use, which is unlike generative models that can generate responses they’ve never seen before. A bit more formally, the input to a retrieval-based model is a context $c$ (the conversation up to this point) and a potential response $r$. The model outputs is a score for the response. To find a good response you would calculate the score for multiple responses and choose the one with the highest score.

Recurrent Neural Network Tutorial, Part 4 – Implementing a GRU/LSTM RNN with Python and Theano

The code for this post is on Github. This is part 4, the last part of the Recurrent Neural Network Tutorial. The previous parts are:

In this post we’ll learn about LSTM (Long Short Term Memory) networks and GRUs (Gated Recurrent Units).  LSTMs were first proposed in 1997 by Sepp Hochreiter and Jürgen Schmidhuber, and are among the most widely used models in Deep Learning for NLP today. GRUs, first used in  2014, are a simpler variant of LSTMs that share many of the same properties.  Let’s start by looking at LSTMs, and then we’ll see how GRUs are different.

Recurrent Neural Networks Tutorial, Part 3 – Backpropagation Through Time and Vanishing Gradients

This the third part of the Recurrent Neural Network Tutorial.

In the previous part of the tutorial we implemented a RNN from scratch, but didn’t go into detail on how Backpropagation Through Time (BPTT) algorithms calculates the gradients. In this part we’ll give a brief overview of BPTT and explain how it differs from traditional backpropagation. We will then try to understand the vanishing gradient problem, which has led to the development of  LSTMs and GRUs, two of the currently most popular and powerful models used in NLP (and other areas). The vanishing gradient problem was originally discovered by Sepp Hochreiter in 1991 and has been receiving attention again recently due to the increased application of deep architectures.

Recurrent Neural Networks Tutorial, Part 2 – Implementing a RNN with Python, Numpy and Theano

This the second part of the Recurrent Neural Network Tutorial. The first part is here.

Code to follow along is on Github.

In this part we will implement a full Recurrent Neural Network from scratch using Python and optimize our implementation using Theano, a library to perform operations on a GPU. The full code is available on Github. I will skip over some boilerplate code that is not essential to understanding Recurrent Neural Networks, but all of that is also on Github.

Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs

Recurrent Neural Networks (RNNs) are popular models that have shown great promise in many NLP tasks. But despite their recent popularity I’ve only found a limited number of resources that throughly explain how RNNs work, and how to implement them. That’s what this tutorial is about. It’s a multi-part series in which I’m planning to cover the following:

As part of the tutorial we will implement a recurrent neural network based language model. The applications of language models are two-fold: First, it allows us to score arbitrary sentences based on how likely they are to occur in the real world. This gives us a measure of grammatical and semantic correctness. Such models are typically used as part of Machine Translation systems. Secondly, a language model allows us to generate new text (I think that’s the much cooler application). Training a language model on Shakespeare allows us to generate Shakespeare-like text. This fun post by Andrej Karpathy demonstrates what character-level language models based on RNNs are capable of.