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 purpose of dropout in the context of RNNs</li>
</ul>

<p>Note: While the models used in the remainder of this course are all LSTMs, the concepts from this section of the course are general to any RNN.</p>


<h2>A. Regularization</h2>

<div id="section1_l4" class="collapse show">
<p>When an RNN has many weight parameters (e.g. the number of hidden units per cell is large or there are multiple RNN layers), it can have a tendency to overfit the training set and therefore generalize poorly to other data. To combat this, we need to <i>regularize</i> the RNN during training.</p>
<p>Regularization refers to modifying the neural network in ways that mitigate the risk of overfitting during training. A particularly popular method of regularization for feed-forward neural networks is <a href="https://en.wikipedia.org/wiki/Dropout_(neural_networks)" target="_blank">dropout</a>. Dropout can also be used in recurrent neural networks, although it works slightly differently.</p>
</div>


<h2>Chapter Goals:</h2>
<ul>
	<li>Understand the purpose of dropout in the context of RNNs</li>
</ul>

<p>Note: While the models used in the remainder of this course are all LSTMs, the concepts from this section of the course are general to any RNN.</p>


<h2>A. Regularization</h2>

<div id="section1_l4">
<p>When an RNN has many weight parameters (e.g. the number of hidden units per cell is large or there are multiple RNN layers), it can have a tendency to overfit the training set and therefore generalize poorly to other data. To combat this, we need to <i>regularize</i> the RNN during training.</p>
<p>Regularization refers to modifying the neural network in ways that mitigate the risk of overfitting during training. A particularly popular method of regularization for feed-forward neural networks is <a href="https://en.wikipedia.org/wiki/Dropout_(neural_networks)" target="_blank">dropout</a>. Dropout can also be used in recurrent neural networks, although it works slightly differently.</p>
</div>


Use dropout to help train a better LSTM model.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Dropout

Chapter Goals:

A. Regularization