Gain insights into processing text data, creating word embeddings, and using LSTMs for semantic analysis and machine translation. Explore industry-relevant NLP techniques with Python and TensorFlow.

nlp_docker.tar.gz

mnist-fashion

In this course you'll learn techniques for processing text data, creating word embeddings, and using long short-term memory networks (LSTM) for tasks such as semantic analysis and machine translation. After completing this course, you will be able to solve the important day-to-day NLP problems faced in industry, which is incredibly useful given the prevalence of text data.

The code for this course is built around the TensorFlow framework, one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. Knowledge of Python and TensorFlow are prerequisites. 

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Natural Language Processing with Machine Learning

<h2 class="section-title">Chapter Goals:</h2>
<ul>
	<li>Understand the differences between feed-forward and recurrent neural networks</li>
	<li>Learn about the long short-term memory (LSTM) cell</li>
</ul>


<h2>A. Neural network types</h2>

<div id="section1_l3" class="collapse show">
<p>As mentioned in the previous chapter, the MLP is a type of <i>feed-forward neural network</i>. This means that each of its layers is a fixed size, and each layer's output is fed into the next layer as input. While feed-forward neural networks are great for tasks involving fixed size input data, they aren't as great in dealing with sequences of text data.</p>
<p>For the remainder of this course, we'll be focusing on <i>recurrent neural networks</i>, which are specially designed to work with sequential data of varying lengths. The main component of a recurrent neural network (RNN) is its <i>cell</i>.</p>
</div>


<p>The rolled RNN diagram shows the "true" depiction of the network. It consists of a single cell (although a multi-layer RNN will have multiple stacked cells), and 3 types of connections: input, output, and recurrent. The unrolled diagram gives us a better look at what each of these connections represent.</p>
<p>In the unrolled diagram above, the RNN consists of 3 time steps, meaning that the length of the RNN's input sequence is 3. This also means that the RNN will output a sequence of length 3. At each time step, the arrow going into the cell represents the token at that particular index of the input sequence. The arrow coming out of the cell represents the cell's output.</p>

> Note: The diagram shows the RNN process for a single input. For batch data, the RNN will handle each individual input independently, in parallel.

<p>The left-to-right arrows connecting the cell at each time step are the recurrent connections. These are the foundation of an RNN, and they represent the transmission of each time step's <i>state</i>. The state gives the cell at the current time step information about the cell inputs and outputs from previous time steps. This is incredibly useful for capturing dependencies in the text that make it easier to calculate probabilities and predictions.</p>

<h2>Chapter Goals:</h2>
<ul>
	<li>Understand the differences between feed-forward and recurrent neural networks</li>
	<li>Learn about the long short-term memory (LSTM) cell</li>
</ul>


<h2>A. Neural network types</h2>

<div id="section1_l3">
<p>As mentioned in the previous chapter, the MLP is a type of <i>feed-forward neural network</i>. This means that each of its layers is a fixed size, and each layer's output is fed into the next layer as input. While feed-forward neural networks are great for tasks involving fixed size input data, they aren't as great in dealing with sequences of text data.</p>
<p>For the remainder of this course, we'll be focusing on <i>recurrent neural networks</i>, which are specially designed to work with sequential data of varying lengths. The main component of a recurrent neural network (RNN) is its <i>cell</i>.</p>
</div>


Learn about recurrent neural networks and LSTM cells.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

RNN/LSTM

Chapter Goals:

A. Neural network types